© 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. 105000
    Prev
    Next
    INDEX
    Explanations

    terms related to biology and ecology

    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
    Calibri
    -0.07
    reh
    -0.06
    Ñĥ
    -0.06
    assadors
    -0.06
    ervations
    -0.06
    .firebaseapp
    -0.06
    minster
    -0.06
    SizePolicy
    -0.06
    大åħ¨
    -0.06
    .writeValue
    -0.05
    POSITIVE LOGITS
    ï¸
    0.09
    ebi
    0.08
    :
    0.07
    ï¼ļ
    0.07
     jenter
    0.07
    _DECLARE
    0.07
    .ERR
    0.07
    egin
    0.07
    _CSS
    0.07
     kapsamında
    0.07
    Activations Density 0.087%

    No Known Activations