© 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. 71975
    Prev
    Next
    INDEX
    Explanations

    terms related to biological stability, functionality, and environmental impact on life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Grammatically coherent phrases and clauses that form complete syntactic units within sentences.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     consc
    -0.09
     sever
    -0.08
    $l
    -0.07
    .Prot
    -0.07
    ÛĮد
    -0.07
    $h
    -0.07
     veter
    -0.07
    _bullet
    -0.07
    arat
    -0.07
    .Dev
    -0.07
    POSITIVE LOGITS
    argin
    0.07
    /stdc
    0.07
    istrovstvÃŃ
    0.07
    ÂŃtion
    0.07
    ½æķ°
    0.06
    átis
    0.06
    Helmet
    0.06
    stadt
    0.06
    ooter
    0.06
    ampo
    0.06
    Activations Density 3.823%

    No Known Activations