© 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. 9-LLAMASCOPE-RES-131K
    11. 95095
    Prev
    Next
    INDEX
    Explanations

    expressions of the word "pretty" or related synonyms indicating a positive assessment

    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
    uars
    -0.08
    ettings
    -0.07
    hist
    -0.07
    ir
    -0.07
    hower
    -0.06
    imer
    -0.06
    odelist
    -0.06
    ooth
    -0.06
    ispens
    -0.06
    ourcem
    -0.06
    POSITIVE LOGITS
    -ÑĤаки
    0.10
    못
    0.08
    âl
    0.08
    OfClass
    0.08
    ../../../
    0.07
    æĦıæĢĿ
    0.07
    _abort
    0.07
    alker
    0.07
    atively
    0.07
    -sized
    0.07
    Activations Density 0.012%

    No Known Activations