© 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. 79787
    Prev
    Next
    INDEX
    Explanations

    statistical information related to demographics and race

    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
    awi
    -0.06
    orno
    -0.06
    regs
    -0.06
     Reg
    -0.06
    ï¸ı
    -0.06
    reg
    -0.05
    lyn
    -0.05
    ç·Ĵ
    -0.05
    å¿ĥ
    -0.05
    .param
    -0.05
    POSITIVE LOGITS
    QRST
    0.07
    etro
    0.07
    brace
    0.07
    ostel
    0.07
    าะ
    0.07
    ntax
    0.07
    rant
    0.06
    VIP
    0.06
    zdy
    0.06
    Ñĭва
    0.06
    Activations Density 0.000%

    No Known Activations