© 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. 124102
    Prev
    Next
    INDEX
    Explanations

    occurrences of the "http" protocol

    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
    allis
    -0.06
    illian
    -0.06
    inae
    -0.06
    edral
    -0.06
    ippo
    -0.06
     arbit
    -0.06
    etri
    -0.06
    illi
    -0.06
    undra
    -0.06
    arih
    -0.06
    POSITIVE LOGITS
    .Compiler
    0.07
    endor
    0.07
    ncy
    0.07
    BuilderInterface
    0.07
    Ł
    0.07
     dÆ°
    0.06
     Amen
    0.06
     Güven
    0.06
    nal
    0.06
    ypad
    0.06
    Activations Density 0.000%

    No Known Activations