© 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. 17772
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names and places related to individuals in the context of notable achievements or events

    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
    142
    -0.07
    adge
    -0.07
    .hs
    -0.06
    inqu
    -0.06
    qx
    -0.06
    InstanceOf
    -0.06
    Fi
    -0.06
    eld
    -0.06
    å§Ĩ
    -0.05
    ingly
    -0.05
    POSITIVE LOGITS
    anke
    0.08
    ervers
    0.07
    avra
    0.07
     Tham
    0.07
    éīĦ
    0.07
    anca
    0.07
    ëŀĢ
    0.07
    ecta
    0.07
    sworth
    0.07
    ono
    0.07
    Activations Density 0.012%

    No Known Activations