© 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. 15-LLAMASCOPE-RES-131K
    11. 62042
    Prev
    Next
    INDEX
    Explanations

    information about individuals' professional backgrounds and experiences

    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
    ocale
    -0.07
    mite
    -0.07
    Äįer
    -0.07
    osen
    -0.07
    tÃŃ
    -0.07
    asz
    -0.06
    ì¸
    -0.06
     flexGrow
    -0.06
    azon
    -0.06
    aty
    -0.06
    POSITIVE LOGITS
    affer
    0.07
    rophe
    0.07
    NEWS
    0.06
     Feder
    0.06
    ingers
    0.06
    ToPoint
    0.06
    aways
    0.06
    OutOfBoundsException
    0.05
    lider
    0.05
    ë¦Ń
    0.05
    Activations Density 0.049%

    No Known Activations