© 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. 9-LLAMASCOPE-RES-131K
    11. 96557
    Prev
    Next
    INDEX
    Explanations

    references to public figures and celebrities

    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
     pl
    -0.07
    amina
    -0.06
     part
    -0.06
     en
    -0.06
    ifact
    -0.06
    eways
    -0.06
    иÑģÑĮ
    -0.06
     gaz
    -0.06
    rious
    -0.06
     plot
    -0.06
    POSITIVE LOGITS
    thal
    0.07
     trä
    0.07
    zman
    0.07
     inan
    0.07
    浩
    0.07
     UNUSED
    0.07
    Direct
    0.06
    urette
    0.06
    cko
    0.06
    annel
    0.06
    Activations Density 0.000%

    No Known Activations