© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95635
    Prev
    Next
    INDEX
    Explanations

    terms related to painting and modeling

    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
    vap
    -0.08
    assi
    -0.07
     Slater
    -0.06
    compact
    -0.06
    ãĥĭãĥĥãĤ¯
    -0.06
    à¥įरमण
    -0.06
    ÙIJÙij
    -0.06
    ÏģÏī
    -0.06
    ErrorException
    -0.06
    heimer
    -0.06
    POSITIVE LOGITS
    377
    0.07
    355
    0.06
    roke
    0.06
    porto
    0.06
    izon
    0.06
    ereo
    0.06
    299
    0.06
    leen
    0.06
    IFA
    0.06
    лоÑĤ
    0.06
    Activations Density 0.002%

    No Known Activations