© 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. 119305
    Prev
    Next
    INDEX
    Explanations

    phrases related to measurements and comparisons

    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
    /goto
    -0.09
    ÅĻad
    -0.08
    اÙĪÙĩ
    -0.08
    _TOOLTIP
    -0.08
    getter
    -0.08
    omik
    -0.08
    ामन
    -0.08
    stup
    -0.08
    getc
    -0.08
    _________________↵↵
    -0.08
    POSITIVE LOGITS
    ents
    0.07
    uras
    0.07
    çļĦæĺ¯
    0.06
    Âł
    0.06
    erm
    0.06
    ien
    0.06
    ys
    0.06
    ollywood
    0.06
    iles
    0.06
    ones
    0.06
    Activations Density 0.026%

    No Known Activations