© 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. 15-LLAMASCOPE-RES-131K
    6. 61851
    Prev
    Next
    INDEX
    Explanations

    references to organizational affiliations or entities

    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
    stad
    -0.06
    pedia
    -0.06
    amac
    -0.06
    abol
    -0.06
    obe
    -0.06
    izzo
    -0.06
    asca
    -0.06
    juana
    -0.06
    lee
    -0.06
     tubes
    -0.06
    POSITIVE LOGITS
    ĨĴ
    0.07
    ÄĽÅ¾
    0.07
    (er
    0.06
    stanov
    0.06
    anh
    0.06
    imet
    0.06
    ients
    0.06
    .EventArgs
    0.06
     turno
    0.06
    aniem
    0.06
    Activations Density 0.006%

    No Known Activations