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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95565
    Prev
    Next
    INDEX
    Explanations

    terms related to various occupations and notable individuals in the entertainment field

    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
    anka
    -0.07
    iben
    -0.07
    atform
    -0.07
    fon
    -0.07
    vanced
    -0.07
    eway
    -0.07
    emme
    -0.07
    okable
    -0.07
    _vlog
    -0.07
    deaux
    -0.07
    POSITIVE LOGITS
    shr
    0.06
    /pub
    0.06
    .PropertyType
    0.06
     cen
    0.06
    zug
    0.05
     Jur
    0.05
     oc
    0.05
     Wars
    0.05
     sponsor
    0.05
    (UINT
    0.05
    Activations Density 0.010%

    No Known Activations