© 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. 30339
    Prev
    Next
    INDEX
    Explanations

    phrases expressing change or transformation

    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
    ãĤ¨ãĥ«
    -0.06
    /AFP
    -0.06
    ulia
    -0.06
    uman
    -0.06
    usercontent
    -0.06
     itself
    -0.06
    isma
    -0.06
    ec
    -0.06
    aggio
    -0.06
    ä¿¡çĶ¨
    -0.06
    POSITIVE LOGITS
     happening
    0.07
    cha
    0.07
     happen
    0.06
    bung
    0.06
     lÃłnh
    0.06
    tatus
    0.06
     kontro
    0.06
    bert
    0.06
    oling
    0.06
    asl
    0.06
    Activations Density 0.013%

    No Known Activations