Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 76442
    Prev
    Next
    INDEX
    Explanations

    programming syntax elements and structure

    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
    ifton
    -0.08
    iffin
    -0.07
    reator
    -0.07
    illis
    -0.07
    alley
    -0.07
    ozem
    -0.06
    imbus
    -0.06
    óż
    -0.06
    ัย
    -0.06
    usercontent
    -0.06
    POSITIVE LOGITS
    _CYCLE
    0.07
     void
    0.07
    TypeInfo
    0.06
    liÄŁe
    0.06
    .dp
    0.06
     Vale
    0.06
    rist
    0.06
    ìº
    0.06
     Soda
    0.06
    _por
    0.06
    Activations Density 0.000%

    No Known Activations