© 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. 82713
    Prev
    Next
    INDEX
    Explanations

    statements emphasizing success and achievements of women

    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
     Bale
    -0.06
    Regards
    -0.06
     conc
    -0.06
     Grat
    -0.06
     Regards
    -0.06
     Axis
    -0.06
     Od
    -0.06
    Ign
    -0.06
    _SRV
    -0.06
    ousse
    -0.06
    POSITIVE LOGITS
    cé
    0.07
     seedu
    0.07
    adar
    0.07
    éf
    0.07
    ieee
    0.07
     gifs
    0.07
    awan
    0.07
    fy
    0.07
    инок
    0.07
    bomb
    0.06
    Activations Density 0.028%

    No Known Activations