© 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. 90419
    Prev
    Next
    INDEX
    Explanations

    programming syntax and constructs, particularly around pointers and return values

    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
    @brief
    -0.08
    ливо
    -0.08
    undy
    -0.08
    arel
    -0.08
    á»ĩn
    -0.07
     JpaRepository
    -0.07
    GuidId
    -0.07
     prostituer
    -0.07
    _lex
    -0.07
    ublik
    -0.07
    POSITIVE LOGITS
     James
    0.06
    rey
    0.06
     Gerr
    0.05
     Fro
    0.05
    ahl
    0.05
     burn
    0.05
    ungle
    0.05
    astics
    0.05
     Eg
    0.05
     anonymous
    0.05
    Activations Density 0.004%

    No Known Activations