© 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. 118393
    Prev
    Next
    INDEX
    Explanations

    references to awards ceremonies, particularly the Oscars and Golden Globes

    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
    rior
    -0.06
    788
    -0.06
    iac
    -0.06
     borderBottom
    -0.06
     bank
    -0.06
    ÙĪØ°
    -0.06
     obs
    -0.06
     Sax
    -0.06
    -in
    -0.06
     Orta
    -0.06
    POSITIVE LOGITS
    ÑĢай
    0.07
     ker
    0.07
     *(*
    0.07
    奴
    0.07
    éł
    0.07
    à¹Ĥà¸ģ
    0.07
    orf
    0.06
    ži
    0.06
    antic
    0.06
    enco
    0.06
    Activations Density 0.006%

    No Known Activations