© 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. 57624
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and coding syntax

    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
    rats
    -0.08
    γκα
    -0.07
    ipy
    -0.07
    PTS
    -0.07
    -Sep
    -0.07
     Erotische
    -0.07
    alles
    -0.07
    actable
    -0.06
    egr
    -0.06
    linkplain
    -0.06
    POSITIVE LOGITS
     getattr
    0.06
     Cruc
    0.06
    getattr
    0.06
    ParameterValue
    0.06
     groove
    0.06
    ushima
    0.05
    ved
    0.05
    .getField
    0.05
     extract
    0.05
    ogn
    0.05
    Activations Density 0.132%

    No Known Activations