© 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. 3907
    Prev
    Next
    INDEX
    Explanations

    biographical information about individuals, particularly their movements and career accomplishments

    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
     trip
    -0.07
     Trip
    -0.06
     travel
    -0.06
    ress
    -0.06
    ts
    -0.06
    ritz
    -0.06
    ict
    -0.05
     relocated
    -0.05
    rc
    -0.05
     control
    -0.05
    POSITIVE LOGITS
     immediate
    0.08
    ãģ¾ãģļ
    0.08
    itom
    0.08
    .UnitTesting
    0.08
     subur
    0.07
    IBUT
    0.07
    Å¡enÃŃ
    0.07
    ubern
    0.07
    vang
    0.07
     ÑģÑĢазÑĥ
    0.07
    Activations Density 0.032%

    No Known Activations