© 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. 30855
    Prev
    Next
    INDEX
    Explanations

    statements about personal characteristics and identities of individuals

    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
    acr
    -0.08
    ilon
    -0.07
    aroo
    -0.07
    eming
    -0.07
    andise
    -0.07
    acent
    -0.07
    oran
    -0.07
     Downs
    -0.07
    bern
    -0.06
    peria
    -0.06
    POSITIVE LOGITS
    zej
    0.07
     tall
    0.07
     fond
    0.07
    zych
    0.07
    nish
    0.06
     wed
    0.06
     mult
    0.06
     apart
    0.06
    cio
    0.06
    ohn
    0.06
    Activations Density 0.021%

    No Known Activations