© 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. 128597
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation indicating significant pauses or transitions in a narrative

    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
     hi
    -0.07
    æ®
    -0.06
     optionally
    -0.06
    sein
    -0.06
    696
    -0.06
    SEG
    -0.06
    TRY
    -0.06
    marker
    -0.06
     ıs
    -0.06
     Cup
    -0.06
    POSITIVE LOGITS
    after
    0.07
     after
    0.07
    Nam
    0.07
    :animated
    0.07
    ando
    0.07
    encer
    0.07
    jian
    0.06
    hone
    0.06
     took
    0.06
    inke
    0.06
    Activations Density 0.021%

    No Known Activations