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

    Neuronpedia

    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. 127407
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'h' or referring to fishing

    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
    illis
    -0.08
    yk
    -0.07
    ↵
    -0.06
    ,
    -0.06
     Kam
    -0.06
    ly
    -0.06
    :
    -0.06
    ault
    -0.06
    ...
    -0.06
     those
    -0.06
    POSITIVE LOGITS
    ContentLoaded
    0.09
    аки
    0.07
    PointerException
    0.07
    ead
    0.07
    itage
    0.07
     tes
    0.07
    OffsetTable
    0.07
     )↵↵↵↵↵↵↵↵
    0.07
    BackingField
    0.07
    apgolly
    0.07
    Activations Density 0.000%

    No Known Activations