© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 86090
    Prev
    Next
    INDEX
    Explanations

    references to decision-making processes and considerations

    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
    arkin
    -0.07
    PropertyValue
    -0.07
    ensi
    -0.07
    enef
    -0.06
    491
    -0.06
    PLICIT
    -0.06
    807
    -0.06
    .increment
    -0.06
    291
    -0.06
    encies
    -0.06
    POSITIVE LOGITS
     determines
    0.14
     matters
    0.13
     mattered
    0.12
     determine
    0.12
     Determines
    0.11
     determining
    0.10
     matter
    0.10
     Matters
    0.10
     plays
    0.10
     affects
    0.10
    Activations Density 0.079%

    No Known Activations