© 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. 9-LLAMASCOPE-RES-131K
    11. 94134
    Prev
    Next
    INDEX
    Explanations

    keywords indicating administrative processes or requirements

    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
    ADIUS
    -0.07
     Rodney
    -0.07
    pak
    -0.07
    ivent
    -0.07
    ỡ
    -0.06
    aiser
    -0.06
    å¤ķ
    -0.06
    zens
    -0.06
    odos
    -0.06
     Suche
    -0.06
    POSITIVE LOGITS
    igm
    0.07
    ugin
    0.07
    igham
    0.06
    ToFront
    0.06
     actionTypes
    0.06
    STALL
    0.06
    KK
    0.06
    imd
    0.06
    uri
    0.06
    Ìģ
    0.06
    Activations Density 0.000%

    No Known Activations