© 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. 59036
    Prev
    Next
    INDEX
    Explanations

    phrases related to recommendations and selections

    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
    iska
    -0.08
    emi
    -0.08
    isa
    -0.07
    erre
    -0.07
    iges
    -0.07
    tam
    -0.07
    iffin
    -0.06
    tical
    -0.06
    lew
    -0.06
    ;br
    -0.06
    POSITIVE LOGITS
    lier
    0.09
    λεκ
    0.06
     McKay
    0.06
    浪
    0.06
     relieved
    0.06
    वत
    0.06
    167
    0.06
    iler
    0.06
    ovÃŃ
    0.06
     sep
    0.06
    Activations Density 0.012%

    No Known Activations