© 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. 98907
    Prev
    Next
    INDEX
    Explanations

    references to educational institutions and experiences

    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
     "
    -0.07
    onth
    -0.07
     prayer
    -0.06
    chw
    -0.06
    imos
    -0.06
     Lun
    -0.06
    unger
    -0.06
    ÑģÑĥÑĤ
    -0.06
    imas
    -0.06
    isinden
    -0.06
    POSITIVE LOGITS
    รà¸ĩ
    0.07
    239
    0.07
    rava
    0.07
    WebResponse
    0.06
    wake
    0.06
     ÐĹа
    0.06
    ecess
    0.06
    OLUTE
    0.06
    347
    0.06
    enna
    0.06
    Activations Density 0.018%

    No Known Activations