© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 55898
    Prev
    Next
    INDEX
    Explanations

    references to specific names or titles, particularly in the context of culture or media

    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
    opoulos
    -0.08
    ToProps
    -0.07
    oine
    -0.07
    er
    -0.07
    ç¬
    -0.07
    ÙĨز
    -0.07
    outes
    -0.07
    ambique
    -0.07
    구
    -0.07
    erca
    -0.07
    POSITIVE LOGITS
    amental
    0.09
    amentals
    0.08
    eb
    0.08
    tv
    0.07
    orf
    0.07
    t
    0.07
    eh
    0.07
    tion
    0.06
    sd
    0.06
    eed
    0.06
    Activations Density 0.014%

    No Known Activations