© 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. 811
    Prev
    Next
    INDEX
    Explanations

    quantitative data or statistics related to population or resources

    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
    ught
    -0.07
    undance
    -0.07
    itored
    -0.07
    luet
    -0.06
    leep
    -0.06
    AuthProvider
    -0.06
    agara
    -0.06
    orate
    -0.06
    228
    -0.06
    uations
    -0.06
    POSITIVE LOGITS
     portion
    0.08
     majority
    0.07
     portions
    0.07
    /Set
    0.07
     Majority
    0.06
    \Lib
    0.06
    ushi
    0.06
    å¦ĥ
    0.06
    ubat
    0.06
    ^K
    0.06
    Activations Density 0.037%

    No Known Activations