© 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. 17-LLAMASCOPE-RES-131K
    11. 118932
    Prev
    Next
    INDEX
    Explanations

    performance metrics and attributes related to athletes or players in sports

    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
    mpar
    -0.07
    andel
    -0.07
    brero
    -0.07
    abra
    -0.07
    ammen
    -0.07
    rette
    -0.07
    avir
    -0.07
    liž
    -0.06
    aud
    -0.06
     Aud
    -0.06
    POSITIVE LOGITS
     شع
    0.08
    áo
    0.06
    VID
    0.06
    Ñĥмов
    0.06
    uga
    0.06
    ignon
    0.06
    nice
    0.06
    -extension
    0.06
    duit
    0.06
    каж
    0.06
    Activations Density 0.005%

    No Known Activations