© 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. 74767
    Prev
    Next
    INDEX
    Explanations

    terms associated with hereditary medical conditions and genetic factors

    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
    .scalablytyped
    -0.12
     Blasio
    -0.07
    aggable
    -0.07
    senal
    -0.07
    PPER
    -0.07
    TEX
    -0.07
    kich
    -0.07
    /WebAPI
    -0.07
    /XMLSchema
    -0.07
    chter
    -0.07
    POSITIVE LOGITS
     versions
    0.07
     or
    0.07
    (!
    0.06
    ably
    0.06
    up
    0.06
    wise
    0.06
    ¤í
    0.06
     Phillips
    0.06
    çīĪ
    0.06
    еко
    0.06
    Activations Density 0.110%

    No Known Activations