© 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. 3265
    Prev
    Next
    INDEX
    Explanations

    mentions of art collectives and community-building initiatives

    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
    foot
    -0.07
     chamber
    -0.06
     Bron
    -0.06
    ìĪĺìĿĺ
    -0.06
     sport
    -0.06
    utter
    -0.06
     afl
    -0.06
     tele
    -0.06
     Appe
    -0.06
     Jerry
    -0.06
    POSITIVE LOGITS
     femmes
    0.09
     femme
    0.08
     Femme
    0.08
    esson
    0.07
    .gg
    0.07
    еви
    0.07
    Visibility
    0.07
    ossil
    0.07
    oningen
    0.07
     Female
    0.07
    Activations Density 0.022%

    No Known Activations