© 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. 104008
    Prev
    Next
    INDEX
    Explanations

    action verbs indicating involvement or contributions

    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
    Scar
    -0.06
    lys
    -0.06
    rai
    -0.06
    116
    -0.06
    %(
    -0.06
    aceutical
    -0.06
    \s
    -0.06
    lec
    -0.06
     pyl
    -0.06
     ench
    -0.06
    POSITIVE LOGITS
    NEG
    0.07
    olina
    0.07
    yleft
    0.07
    nces
    0.07
    oggles
    0.07
    indows
    0.07
    ublik
    0.07
     finish
    0.06
     Linh
    0.06
    .objects
    0.06
    Activations Density 0.121%

    No Known Activations