© 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. 104155
    Prev
    Next
    INDEX
    Explanations

    references to the number one or concepts of singularity

    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
    ennon
    -0.07
    à¸Ļà¹Ģà¸ķ
    -0.07
    ington
    -0.06
    寸
    -0.06
    รà¸ĵ
    -0.06
    ware
    -0.06
    exo
    -0.06
    виг
    -0.06
    styleType
    -0.06
    ipay
    -0.06
    POSITIVE LOGITS
    ocre
    0.08
    uda
    0.07
    ty
    0.07
    Ŀ
    0.07
    itas
    0.06
    té
    0.06
    iner
    0.06
    odied
    0.06
    好çļĦ
    0.06
    self
    0.06
    Activations Density 0.013%

    No Known Activations