© 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. 124663
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and regulatory contexts

    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
    antal
    -0.08
    ãģ£ãģ±ãģĦ
    -0.06
    aleza
    -0.06
    ropa
    -0.06
    elsius
    -0.06
    oya
    -0.06
     puss
    -0.06
    opher
    -0.06
    SizePolicy
    -0.06
    oslav
    -0.06
    POSITIVE LOGITS
    lessly
    0.08
    raquo
    0.07
    gger
    0.06
    xCE
    0.06
    vice
    0.06
    /of
    0.06
     WaitForSeconds
    0.06
    иÑĤом
    0.06
    MeasureSpec
    0.06
    outh
    0.06
    Activations Density 0.314%

    No Known Activations