© 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. 76180
    Prev
    Next
    INDEX
    Explanations

    programming concepts related to error handling and parameterization

    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
    ulen
    -0.08
    eman
    -0.07
     syndrome
    -0.06
     Syndrome
    -0.06
    ysz
    -0.06
    .communication
    -0.06
    ake
    -0.06
    ptal
    -0.06
    ption
    -0.06
    aul
    -0.06
    POSITIVE LOGITS
     anderen
    0.07
    icing
    0.07
     hung
    0.06
     jadx
    0.06
     copy
    0.06
    hang
    0.06
    _COPY
    0.06
     hang
    0.06
     andere
    0.06
    iltr
    0.06
    Activations Density 0.001%

    No Known Activations