Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95970
    Prev
    Next
    INDEX
    Explanations

    references to art exhibitions

    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
    409
    -0.07
    anta
    -0.06
    rol
    -0.06
    aji
    -0.06
    540
    -0.06
    lette
    -0.06
    rita
    -0.06
    438
    -0.06
    itas
    -0.06
     sund
    -0.06
    POSITIVE LOGITS
    createFrom
    0.07
    oldur
    0.07
    acre
    0.07
    .sponge
    0.06
    .appspot
    0.06
     Sno
    0.06
    ãĤ¸ãĤ§
    0.06
    _nf
    0.06
     æĦĽ
    0.06
    nesc
    0.06
    Activations Density 0.043%

    No Known Activations