© 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 EvalsExportsinterp-engineNEWAPI 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. 97740
    Prev
    Next
    INDEX
    Explanations

    phrases related to rankings and categories of significance

    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
    phinx
    -0.08
    .mybatisplus
    -0.08
    ifornia
    -0.08
    amine
    -0.07
    orgia
    -0.07
    teness
    -0.07
    кÑģ
    -0.07
    дина
    -0.07
    ahoma
    -0.07
    itemap
    -0.07
    POSITIVE LOGITS
    -
    0.06
    ios
    0.06
    neck
    0.06
     ani
    0.06
    bei
    0.05
     Bene
    0.05
    imer
    0.05
     scatter
    0.05
    ateg
    0.05
     Murdoch
    0.05
    Activations Density 0.034%

    No Known Activations