© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 63301
    Prev
    Next
    INDEX
    Explanations

    specific skills and qualifications for committee nominations

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ould
    -0.07
    id
    -0.07
    andy
    -0.07
    anken
    -0.06
    ange
    -0.06
    ent
    -0.06
    ingham
    -0.06
    bred
    -0.06
    agh
    -0.06
    by
    -0.06
    POSITIVE LOGITS
     etc
    0.12
    etc
    0.11
     ÑĤоÑīо
    0.08
    -LAST
    0.08
    Additionally
    0.08
    Č↵
    0.08
    ãģĿãģĹãģ¦
    0.08
     기íĥĢ
    0.08
    iferay
    0.07
    ToWorld
    0.07
    Activations Density 0.026%

    No Known Activations