© 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. 78149
    Prev
    Next
    INDEX
    Explanations

    symbols or formatting elements associated with programming or coding languages

    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
     wheel
    -0.07
    edii
    -0.07
     lock
    -0.06
    elig
    -0.06
    aits
    -0.06
    lock
    -0.06
    uum
    -0.06
     Garten
    -0.06
    ester
    -0.06
    важа
    -0.06
    POSITIVE LOGITS
    à¤ķरण
    0.08
     san
    0.07
    antal
    0.07
    ãĤ
    0.07
     saint
    0.06
    aison
    0.06
    IPS
    0.06
    shield
    0.06
    onnement
    0.06
     phá»iji
    0.06
    Activations Density 0.001%

    No Known Activations