© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 8-LLAMASCOPE-RES-32K
    11. 29490
    Prev
    Next
    INDEX
    Explanations

    specific names and notable titles, particularly related to Danish culture and history

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Danish or Nordic names, places, and language elements.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @danielepoterti
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    öh
    -0.15
    bright
    -0.15
    ãĤģ
    -0.15
    aire
    -0.15
    kontakte
    -0.14
    .Misc
    -0.14
    å¯Ĩ
    -0.14
    _ipc
    -0.14
    _alt
    -0.13
    /Framework
    -0.13
    POSITIVE LOGITS
    .dk
    0.21
    bjerg
    0.18
    ål
    0.16
    gaard
    0.16
     Waterloo
    0.16
    alborg
    0.16
     fj
    0.15
    borg
    0.15
     Nielsen
    0.15
     Oslo
    0.15
    Activations Density 0.233%

    No Known Activations