© 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. 9-LLAMASCOPE-RES-131K
    11. 95481
    Prev
    Next
    INDEX
    Explanations

    instance of significant occurrences and events

    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
    acher
    -0.08
    deaux
    -0.08
    uf
    -0.07
    assen
    -0.07
    senal
    -0.07
    taboola
    -0.07
    (jq
    -0.07
    asel
    -0.07
    LIBINT
    -0.07
    iyas
    -0.06
    POSITIVE LOGITS
     Kar
    0.06
    mey
    0.06
    REV
    0.06
     Dün
    0.06
    oret
    0.05
     Orr
    0.05
     Mate
    0.05
    çľģ
    0.05
     Kraft
    0.05
     Lever
    0.05
    Activations Density 0.048%

    No Known Activations