© 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. 116643
    Prev
    Next
    INDEX
    Explanations

    descriptions of political or ideological extremes

    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
    KeyEvent
    -0.08
    zar
    -0.07
    owitz
    -0.07
     resil
    -0.07
     Redux
    -0.07
    antz
    -0.07
    parm
    -0.06
    ì£
    -0.06
     licens
    -0.06
    899
    -0.06
    POSITIVE LOGITS
    а
    0.07
    urdy
    0.06
    çŁ¢
    0.06
     dialect
    0.06
    е
    0.06
     Edison
    0.06
     Realty
    0.06
    omy
    0.06
    nj
    0.05
    !..
    0.05
    Activations Density 0.002%

    No Known Activations