© 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. 16422
    Prev
    Next
    INDEX
    Explanations

    numerical values in a structured or complex format

    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
    s
    -0.08
    icari
    -0.07
    #ae
    -0.06
    #aa
    -0.06
    issors
    -0.06
    itler
    -0.06
    lood
    -0.06
    visor
    -0.06
    oron
    -0.06
    opic
    -0.06
    POSITIVE LOGITS
    fq
    0.07
    ONA
    0.07
    ALS
    0.07
    unctuation
    0.07
    261
    0.07
    FieldType
    0.07
    ibel
    0.06
    .GroupLayout
    0.06
    ipa
    0.06
    SAVE
    0.06
    Activations Density 0.000%

    No Known Activations