© 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. 55070
    Prev
    Next
    INDEX
    Explanations

    characters and punctuation used in formal document formats

    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
    abee
    -0.07
    rove
    -0.06
    ................................................................
    -0.06
    amil
    -0.06
    unda
    -0.06
    rief
    -0.06
    uen
    -0.05
     нап
    -0.05
    uien
    -0.05
    ycz
    -0.05
    POSITIVE LOGITS
    Ľå»º
    0.08
    zig
    0.08
     sécur
    0.08
    олаг
    0.07
     Hancock
    0.07
    klä
    0.07
    iš
    0.07
    ãĥĭãĤ¢
    0.07
    oš
    0.07
    igidBody
    0.07
    Activations Density 0.001%

    No Known Activations