© 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. 77562
    Prev
    Next
    INDEX
    Explanations

    references to various attributes and conditions in technical or procedural contexts

    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
    lh
    -0.06
    urgeon
    -0.06
    /widget
    -0.06
    unger
    -0.06
     Trev
    -0.06
    afi
    -0.06
    widget
    -0.05
     truth
    -0.05
     immature
    -0.05
    abwe
    -0.05
    POSITIVE LOGITS
    æºIJ
    0.08
     source
    0.08
     location
    0.08
     Source
    0.07
     occasion
    0.07
     circuit
    0.07
    source
    0.07
     Ulus
    0.07
    aryl
    0.07
    estro
    0.07
    Activations Density 0.060%

    No Known Activations