© 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. 15-LLAMASCOPE-RES-131K
    11. 103617
    Prev
    Next
    INDEX
    Explanations

    mentions of small and medium-sized containers or utensils

    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
    acio
    -0.07
    andas
    -0.07
    elia
    -0.07
    пеÑĩ
    -0.07
    798
    -0.06
    ardy
    -0.06
     دÙģ
    -0.06
    zá
    -0.06
    .normalized
    -0.06
    igu
    -0.06
    POSITIVE LOGITS
     Lif
    0.07
    ãĥ¼ãĥ©
    0.07
     Shelf
    0.07
    oyo
    0.07
    gypt
    0.07
    oteca
    0.07
    ABL
    0.07
     Simpson
    0.06
    olor
    0.06
    ogg
    0.06
    Activations Density 0.003%

    No Known Activations