© 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. 83032
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating movement or direction

    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
     VÅ¡ech
    -0.09
    umbn
    -0.08
    CTIONS
    -0.08
     jadx
    -0.07
    kah
    -0.07
    ARGIN
    -0.07
    /people
    -0.07
    SGlobal
    -0.07
    IMARY
    -0.07
    еко
    -0.07
    POSITIVE LOGITS
     the
    0.11
     some
    0.10
     a
    0.08
    /down
    0.08
    /off
    0.07
     what
    0.07
    wards
    0.07
     an
    0.07
     those
    0.07
    çļĦæĺ¯
    0.07
    Activations Density 0.089%

    No Known Activations