© 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 EvalsExportsAPI 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. 106720
    Prev
    Next
    INDEX
    Explanations

    references to explicit language and adult themes

    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
    ollapse
    -0.07
    arella
    -0.07
    ssi
    -0.07
    olio
    -0.07
    odule
    -0.06
    erah
    -0.06
    ONEY
    -0.06
    folio
    -0.06
    izo
    -0.06
     LUA
    -0.06
    POSITIVE LOGITS
     ÙħاÙĥ
    0.06
    åł´
    0.06
     oc
    0.06
    unga
    0.06
    _misc
    0.06
    )NULL
    0.06
    миÑĢ
    0.06
    oser
    0.06
    /misc
    0.06
    .Restrict
    0.06
    Activations Density 0.004%

    No Known Activations