© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 117171
    Prev
    Next
    INDEX
    Explanations

    statements that define or explain concepts and meanings

    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
    sj
    -0.07
    ëĭī
    -0.07
    Ñı
    -0.07
    ìłĢ
    -0.07
    egas
    -0.07
    ække
    -0.07
    eki
    -0.07
    /remove
    -0.07
    ायत
    -0.07
    lama
    -0.07
    POSITIVE LOGITS
    ly
    0.10
    lessly
    0.10
    fully
    0.10
     ones
    0.08
    less
    0.08
    :
    0.07
    istar
    0.07
    ful
    0.07
    LY
    0.06
    tons
    0.06
    Activations Density 0.003%

    No Known Activations