© 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. 84434
    Prev
    Next
    INDEX
    Explanations

    references to customer service and positive experiences with individuals

    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
    ansi
    -0.07
    agua
    -0.06
     Mein
    -0.06
    isine
    -0.06
     volumes
    -0.06
    Alias
    -0.06
     Urban
    -0.06
     lá»ĩ
    -0.06
    Gro
    -0.06
    jen
    -0.06
    POSITIVE LOGITS
     Assigned
    0.07
     handwritten
    0.06
    bral
    0.06
     Mour
    0.06
    fast
    0.06
    bservable
    0.06
    ingle
    0.06
    ıģ
    0.06
    lename
    0.06
     Polynomial
    0.06
    Activations Density 0.009%

    No Known Activations