© 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. 40189
    Prev
    Next
    INDEX
    Explanations

    phrases related to environmental data and land imagery

    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
    ichert
    -0.08
    reate
    -0.06
    ransition
    -0.06
    itto
    -0.06
    render
    -0.06
    _iff
    -0.06
    ression
    -0.06
     Overse
    -0.06
    ɵ
    -0.06
    atem
    -0.06
    POSITIVE LOGITS
     conv
    0.07
     ALERT
    0.07
    iles
    0.07
    ÑĪÑĤ
    0.07
     Seks
    0.06
    aky
    0.06
     Фед
    0.06
     ê²
    0.06
    erten
    0.06
    .nc
    0.06
    Activations Density 0.000%

    No Known Activations