© 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. 119489
    Prev
    Next
    INDEX
    Explanations

    mentions of universities and academic institutions

    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
     kro
    -0.06
    immer
    -0.06
    olean
    -0.06
    rane
    -0.06
    velt
    -0.06
    loom
    -0.06
    425
    -0.06
    elle
    -0.06
     CSL
    -0.06
    .Fields
    -0.06
    POSITIVE LOGITS
    icros
    0.07
     <*>
    0.07
     éĥ
    0.07
    æŀ
    0.06
     Cav
    0.06
     Graves
    0.06
    cimal
    0.06
    ienes
    0.06
    ski
    0.06
    пÑĢиклад
    0.06
    Activations Density 0.023%

    No Known Activations