© 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. 87544
    Prev
    Next
    INDEX
    Explanations

    names of individuals involved in entertainment or artistic production

    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
    lech
    -0.07
     NOP
    -0.06
    NOP
    -0.06
    latlong
    -0.06
    untu
    -0.06
    ledge
    -0.06
    олж
    -0.06
    reen
    -0.06
    æ²ĸ
    -0.06
    ichi
    -0.06
    POSITIVE LOGITS
    BOOLE
    0.07
     Backpack
    0.07
     Ùħتر
    0.06
    sek
    0.06
    thalm
    0.06
     ttk
    0.06
    DAQ
    0.06
    hoff
    0.06
    Shortcut
    0.06
    anco
    0.06
    Activations Density 0.016%

    No Known Activations