© 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. 15119
    Prev
    Next
    INDEX
    Explanations

    instances related to familial relationships and connections

    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
    assin
    -0.08
    ughs
    -0.07
    linger
    -0.07
    avl
    -0.07
    aty
    -0.07
    utes
    -0.07
    GRAM
    -0.06
    -CN
    -0.06
    alse
    -0.06
    SDL
    -0.06
    POSITIVE LOGITS
     guy
    0.07
    éĤ£ä¸ª
    0.07
     unnamed
    0.07
     man
    0.07
    ContextHolder
    0.07
     someone
    0.06
     woman
    0.06
     niche
    0.06
    atoon
    0.06
     young
    0.06
    Activations Density 0.036%

    No Known Activations