© 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. 3168
    Prev
    Next
    INDEX
    Explanations

    descriptions of food texture and flavor

    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
     Bir
    -0.06
    igg
    -0.06
     pract
    -0.06
    ceu
    -0.06
    }elseif
    -0.06
    .intellij
    -0.06
    uve
    -0.06
    isz
    -0.06
     Zug
    -0.06
    icl
    -0.06
    POSITIVE LOGITS
    Âĭ
    0.07
    ÂĽ
    0.07
     balances
    0.07
     balance
    0.07
     Balance
    0.06
    balances
    0.06
    .balance
    0.06
    balance
    0.06
    rogate
    0.06
    aghan
    0.06
    Activations Density 0.007%

    No Known Activations