© 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. 76784
    Prev
    Next
    INDEX
    Explanations

    references to articles or publications

    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
    Ø®ÙĪاÙĨ
    -0.06
    }elseif
    -0.06
    /Gate
    -0.06
     Davies
    -0.06
    se
    -0.06
    oken
    -0.06
    midi
    -0.06
    stem
    -0.06
    inton
    -0.05
     whisky
    -0.05
    POSITIVE LOGITS
    adero
    0.08
    singleton
    0.07
    оÑģÑĥд
    0.07
    gies
    0.07
    ливо
    0.06
    uktur
    0.06
    enames
    0.06
    jÃŃt
    0.06
    uraa
    0.06
    cht
    0.06
    Activations Density 0.023%

    No Known Activations