© 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. 16221
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "coincide" and its variations

    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
    bao
    -0.07
    ete
    -0.07
    out
    -0.07
    eller
    -0.06
    /th
    -0.06
    aren
    -0.06
    ahu
    -0.06
    self
    -0.06
    pez
    -0.06
    _warnings
    -0.06
    POSITIVE LOGITS
     with
    0.11
    ingly
    0.10
     vỼi
    0.09
    WithString
    0.08
    //{{
    0.08
    villa
    0.07
    WithData
    0.07
    à¹ĩà¸ĩ
    0.07
    _Lean
    0.07
    oÄŁ
    0.07
    Activations Density 0.004%

    No Known Activations