© 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. 98979
    Prev
    Next
    INDEX
    Explanations

    expressions and reactions related to personal achievements and public responses

    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
    avra
    -0.08
    ipur
    -0.07
    aits
    -0.07
    alez
    -0.07
    viron
    -0.07
    rior
    -0.07
    รà¸ĵ
    -0.07
    ahr
    -0.07
    eç
    -0.07
    weg
    -0.06
    POSITIVE LOGITS
     himself
    0.06
    ÑĨи
    0.06
    æī
    0.06
     GObject
    0.06
    una
    0.06
     Mam
    0.05
    endo
    0.05
     Himself
    0.05
    ãĥ»ãĥ»ãĥ»
    0.05
     Provid
    0.05
    Activations Density 0.041%

    No Known Activations