© 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. 17-LLAMASCOPE-RES-131K
    11. 15105
    Prev
    Next
    INDEX
    Explanations

    connections and components in technical or mechanical descriptions

    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
    phin
    -0.07
     relationship
    -0.07
    _idxs
    -0.07
    olini
    -0.07
    ãĢģãģĿãģĨ
    -0.06
    engo
    -0.06
    ussen
    -0.06
    stadt
    -0.06
    -inf
    -0.06
    .Dto
    -0.06
    POSITIVE LOGITS
    >Main
    0.07
     Ùħباش
    0.07
    Brains
    0.07
    èŃ
    0.06
    nout
    0.06
    ноÑģ
    0.06
     Tee
    0.06
    ãĥĥãĤ¯
    0.06
    erosis
    0.06
    .equ
    0.06
    Activations Density 0.054%

    No Known Activations