© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 76828
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods

    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
     spokesman
    -0.06
    ض
    -0.06
     Serie
    -0.06
    rag
    -0.06
    ÙĦÙĦ
    -0.06
    еÑĢÑĮ
    -0.06
     must
    -0.06
     series
    -0.06
     GetLastError
    -0.05
    ضÙĬ
    -0.05
    POSITIVE LOGITS
    ourd
    0.07
    omon
    0.07
    elfast
    0.06
    umm
    0.06
    enzhen
    0.06
     pilots
    0.06
    .community
    0.06
    egan
    0.06
     pil
    0.06
     swallow
    0.06
    Activations Density 0.000%

    No Known Activations