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

    Neuronpedia

    Jacobian LensNEW
    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. 15-LLAMASCOPE-RES-131K
    11. 88134
    Prev
    Next
    INDEX
    Explanations

    descriptions of dimensions and weights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uard
    -0.07
     lip
    -0.07
     lips
    -0.07
    üz
    -0.06
    egis
    -0.06
    ł
    -0.06
    sar
    -0.06
    sel
    -0.06
     Hundred
    -0.06
    ivas
    -0.06
    POSITIVE LOGITS
    ì§ľ
    0.09
    chai
    0.07
    odd
    0.07
    vette
    0.07
    addle
    0.07
    å·¦åı³
    0.07
    eters
    0.07
    adia
    0.07
    ëĨ
    0.07
    °ëĭ¤
    0.07
    Activations Density 0.030%

    No Known Activations