© 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. 82755
    Prev
    Next
    INDEX
    Explanations

    references to favorite things or personal preferences

    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
    oved
    -0.07
    ugar
    -0.06
    zens
    -0.06
     Mal
    -0.06
     moci
    -0.06
    _$_
    -0.06
    uluk
    -0.06
    istor
    -0.06
    \Context
    -0.06
    _WRAP
    -0.06
    POSITIVE LOGITS
    kah
    0.07
    LogLevel
    0.07
     rule
    0.07
    nout
    0.07
    ï¸
    0.06
    702
    0.06
    bsite
    0.06
    alim
    0.06
    AGMENT
    0.06
     addCriterion
    0.06
    Activations Density 0.006%

    No Known Activations