© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 91976
    Prev
    Next
    INDEX
    Explanations

    punctuation symbols and other formatting characters

    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
    Âł
    -0.06
     Sax
    -0.06
     Synd
    -0.06
    e
    -0.06
     ï
    -0.05
     Cav
    -0.05
     Â
    -0.05
    .ravel
    -0.05
    ousel
    -0.05
    ystore
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.08
    oreferrer
    0.08
    \Blueprint
    0.07
    OffsetTable
    0.07
    APT
    0.07
    esser
    0.07
     targetType
    0.07
    iot
    0.07
    .ResponseWriter
    0.07
    ÑģÑĤоÑĢ
    0.07
    Activations Density 0.004%

    No Known Activations