© 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. 25-LLAMASCOPE-RES-32K
    11. 17480
    Prev
    Next
    INDEX
    Explanations

    references to historical events and context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rnd
    -0.14
    alous
    -0.14
    Translator
    -0.14
    opp
    -0.13
    ukkan
    -0.13
    ses
    -0.13
    еÑĢин
    -0.13
    oret
    -0.13
    วรร
    -0.13
    μεν
    -0.13
    POSITIVE LOGITS
     history
    1.28
    history
    1.09
     History
    1.09
     HISTORY
    1.00
    History
    0.97
    -history
    0.96
    _history
    0.90
     histories
    0.87
    .history
    0.84
     Geschichte
    0.80
    Activations Density 0.379%

    No Known Activations