© 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. 126437
    Prev
    Next
    INDEX
    Explanations

    terms related to geological features and cosmic events

    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
    xious
    -0.07
    anka
    -0.07
     (...)
    -0.07
    Ñĥки
    -0.07
    ":"","
    -0.06
    á»ĵn
    -0.06
    .Enc
    -0.06
    adays
    -0.06
    (&$
    -0.06
    trak
    -0.06
    POSITIVE LOGITS
    ebin
    0.07
    μοί
    0.07
    лина
    0.06
     RESERVED
    0.06
    uell
    0.06
    isex
    0.06
    utan
    0.06
    ason
    0.06
    ä¹İ
    0.06
     UNKNOWN
    0.06
    Activations Density 0.000%

    No Known Activations