© 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. 117894
    Prev
    Next
    INDEX
    Explanations

    words related to content submission and publication

    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
    ember
    -0.06
    asta
    -0.06
     Tracy
    -0.06
     Wish
    -0.06
    opak
    -0.05
    abaj
    -0.05
     tr
    -0.05
    acket
    -0.05
    ewood
    -0.05
    atar
    -0.05
    POSITIVE LOGITS
    andler
    0.08
    _DIAG
    0.08
    ÙĪÙĦÙĬÙĪ
    0.07
    Disposition
    0.07
    toFloat
    0.07
    uito
    0.07
    _Callback
    0.07
    INY
    0.07
    .opensource
    0.07
    unfold
    0.07
    Activations Density 0.001%

    No Known Activations