© 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. 103674
    Prev
    Next
    INDEX
    Explanations

    references to specific works of literature or film

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Punctuation (primarily commas) following the titles of creative works, scientific names, or specialized terminology in formal or academic writing.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     Tf
    -0.07
    اÙĨ
    -0.06
    anning
    -0.06
     Bros
    -0.06
    chai
    -0.06
     grav
    -0.06
    бÑĥд
    -0.06
    款
    -0.06
     banc
    -0.06
    lere
    -0.06
    POSITIVE LOGITS
    <\/
    0.08
     ,
    0.08
    itters
    0.07
    ï¸ı
    0.07
    leftright
    0.07
     Âł
    0.07
    piel
    0.06
    ipsis
    0.06
    ropa
    0.06
    cz
    0.06
    Activations Density 0.176%

    No Known Activations