© 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. 31398
    Prev
    Next
    INDEX
    Explanations

    HTML table structures and their attributes

    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
    veau
    -0.08
    zik
    -0.08
    βά
    -0.07
    ameda
    -0.07
    thood
    -0.06
    rahim
    -0.06
    ÑĤаб
    -0.06
    476
    -0.06
    _gettime
    -0.06
    ivia
    -0.06
    POSITIVE LOGITS
    опол
    0.06
    Å¡ov
    0.06
     doma
    0.06
    ialog
    0.06
    abwe
    0.06
     Playback
    0.06
    panse
    0.06
    кÑĢа
    0.06
     offsetof
    0.06
    unar
    0.06
    Activations Density 0.004%

    No Known Activations