© 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. 15-LLAMASCOPE-RES-131K
    11. 897
    Prev
    Next
    INDEX
    Explanations

    dates and times referenced in the text

    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
    ymb
    -0.07
    asset
    -0.07
    ä½įäºİ
    -0.07
    ffa
    -0.07
    ilion
    -0.06
    uffix
    -0.06
    urator
    -0.06
    ä½įæĸ¼
    -0.06
    :host
    -0.06
    ucz
    -0.06
    POSITIVE LOGITS
    ya
    0.07
    plist
    0.07
    comings
    0.06
    gebn
    0.06
    lingen
    0.06
    .Accessible
    0.06
    _blocking
    0.06
     ore
    0.06
     bidi
    0.06
     provid
    0.06
    Activations Density 0.060%

    No Known Activations