© 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. 124499
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and other non-alphanumeric 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
    ád
    -0.07
    trap
    -0.07
    stüt
    -0.07
    rocessing
    -0.06
    ghi
    -0.06
    ophy
    -0.06
     cond
    -0.06
    vÄĽd
    -0.06
    ietf
    -0.06
    ichert
    -0.06
    POSITIVE LOGITS
     sic
    0.08
    (em
    0.07
    sic
    0.07
    emphasis
    0.07
    zes
    0.07
    zia
    0.06
     Amen
    0.06
    phasis
    0.06
    phin
    0.06
    avec
    0.06
    Activations Density 0.058%

    No Known Activations