© 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. 69318
    Prev
    Next
    INDEX
    Explanations

    variations of the name "Castell" and similar terms

    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
    addin
    -0.07
    bst
    -0.07
    opens
    -0.06
    Ðİ
    -0.06
    IXEL
    -0.06
    볨
    -0.06
     facult
    -0.06
    .emf
    -0.06
    ATOM
    -0.06
    kinson
    -0.06
    POSITIVE LOGITS
    agner
    0.09
     Cast
    0.08
    aigned
    0.08
    orp
    0.07
    Č↵
    0.07
    etter
    0.07
     CAST
    0.07
    CAST
    0.07
    ivec
    0.07
    rophic
    0.07
    Activations Density 0.005%

    No Known Activations