© 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. 29338
    Prev
    Next
    INDEX
    Explanations

    quantitative data relating to populations and statistics

    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
    Ÿ
    -0.07
    _atual
    -0.07
    opol
    -0.07
     reh
    -0.07
    708
    -0.06
    ilo
    -0.06
     å§
    -0.06
    libft
    -0.06
    iga
    -0.06
    203
    -0.06
    POSITIVE LOGITS
     years
    0.06
     slap
    0.06
    aturas
    0.06
    atoi
    0.06
    ZF
    0.06
    fish
    0.06
     Richmond
    0.06
    ekim
    0.06
    umber
    0.06
    olk
    0.06
    Activations Density 0.033%

    No Known Activations