© 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. 84655
    Prev
    Next
    INDEX
    Explanations

    references to individuals with notable skills or achievements, particularly in artistic or intellectual fields

    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
     Setter
    -0.06
    lund
    -0.06
     regime
    -0.06
    _CHARSET
    -0.05
    umba
    -0.05
    ARGV
    -0.05
     ellipt
    -0.05
    abant
    -0.05
     cart
    -0.05
     Helmet
    -0.05
    POSITIVE LOGITS
     chess
    0.11
     ÑĪаÑħ
    0.11
     Chess
    0.10
    æ£ĭ
    0.10
    Chess
    0.09
    åĽ²
    0.07
    /lic
    0.07
    ìĹ´
    0.07
    etik
    0.07
    itest
    0.07
    Activations Density 0.012%

    No Known Activations