© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 55900
    Prev
    Next
    INDEX
    Explanations

    special characters or formatting symbols

    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
    in
    -0.08
    ÑĨик
    -0.07
    aye
    -0.07
    phin
    -0.06
    pok
    -0.06
    P
    -0.06
    Ñģм
    -0.06
    obec
    -0.06
    oge
    -0.06
     Inner
    -0.06
    POSITIVE LOGITS
    ullo
    0.07
    anford
    0.06
    (Keys
    0.06
    íĭĢ
    0.06
    ardy
    0.06
     demonstr
    0.06
     imperson
    0.06
     tread
    0.06
     nomin
    0.06
     thumb
    0.06
    Activations Density 0.006%

    No Known Activations