© 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. 18-LLAMASCOPE-RES-32K
    11. 27595
    Prev
    Next
    INDEX
    Explanations

    highly specific terms and phrases related to precision and targets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    óst
    -0.15
    سÙĪب
    -0.15
    achsen
    -0.15
    dek
    -0.15
    iddet
    -0.15
    /vnd
    -0.14
     LENG
    -0.14
    ophe
    -0.14
    ož
    -0.14
    [assembly
    -0.14
    POSITIVE LOGITS
    .Syntax
    0.15
    _OM
    0.14
    omat
    0.14
     Fleet
    0.14
     Barrett
    0.14
    ATEGORY
    0.13
     Henderson
    0.13
    cede
    0.13
    557
    0.13
     fleet
    0.13
    Activations Density 0.006%

    No Known Activations