© 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. 57266
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and sentence endings

    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
    bout
    -0.07
    .setUp
    -0.06
     Butler
    -0.06
    _HINT
    -0.06
    Ñıгом
    -0.06
    BSD
    -0.06
    BT
    -0.06
    iá»ģn
    -0.06
     Worse
    -0.06
    iferay
    -0.05
    POSITIVE LOGITS
     but
    0.28
     however
    0.23
     However
    0.23
     nhÆ°ng
    0.23
     BUT
    0.21
    but
    0.21
     pero
    0.21
     But
    0.20
    However
    0.20
    ï¼Įä½Ĩ
    0.20
    Activations Density 0.360%

    No Known Activations