© 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. 9-LLAMASCOPE-RES-131K
    11. 97755
    Prev
    Next
    INDEX
    Explanations

    elements reflecting relationships and social dynamics

    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
    hdl
    -0.07
    PRS
    -0.07
    braco
    -0.06
    egot
    -0.06
    497
    -0.06
    swer
    -0.06
     Sheridan
    -0.06
    ouro
    -0.06
    venge
    -0.06
    ÙİÙĨ
    -0.06
    POSITIVE LOGITS
    füh
    0.07
    еÑĢп
    0.07
     Bonds
    0.07
    jav
    0.06
    kap
    0.06
    ueur
    0.06
    ERO
    0.06
    ÃŃg
    0.06
    iy
    0.06
    ahat
    0.06
    Activations Density 0.020%

    No Known Activations