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

    Neuronpedia

    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. 82184
    Prev
    Next
    INDEX
    Explanations

    mentions of the actress Tiffany Haddish

    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
    prepend
    -0.07
    dek
    -0.07
    cept
    -0.06
    hum
    -0.06
    tera
    -0.06
    vel
    -0.06
    ì°
    -0.06
    terra
    -0.06
    mino
    -0.06
    oa
    -0.05
    POSITIVE LOGITS
    entially
    0.09
    ean
    0.09
     GANG
    0.08
    UND
    0.07
    ellation
    0.07
     Hacker
    0.07
    ording
    0.07
    CTOR
    0.07
    entlich
    0.07
    ibbon
    0.07
    Activations Density 0.003%

    No Known Activations