© 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. 56288
    Prev
    Next
    INDEX
    Explanations

    references to awards and licensing in professional contexts

    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
    /respond
    -0.06
     Norton
    -0.06
    æĥħ
    -0.06
    wi
    -0.06
    noop
    -0.06
    icha
    -0.06
    anga
    -0.06
     gal
    -0.06
    gend
    -0.05
    оза
    -0.05
    POSITIVE LOGITS
     reserved
    0.10
    reserved
    0.09
    _reserved
    0.08
     rare
    0.08
     Reserved
    0.08
    Reserved
    0.08
    elite
    0.08
    วà¸ĩ
    0.08
     RESERVED
    0.08
    /***/
    0.08
    Activations Density 0.032%

    No Known Activations