© 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. 125587
    Prev
    Next
    INDEX
    Explanations

    references to boards and their members or governance structures

    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
    raj
    -0.07
    illi
    -0.07
    pliers
    -0.07
    нед
    -0.07
     Kostenlos
    -0.07
    atile
    -0.06
    ycz
    -0.06
    okie
    -0.06
    ats
    -0.06
    forge
    -0.06
    POSITIVE LOGITS
    walk
    0.11
     board
    0.09
    (*)(
    0.07
    (Board
    0.07
    .Board
    0.07
    /board
    0.07
    ozo
    0.07
    hani
    0.07
    wide
    0.07
     Board
    0.07
    Activations Density 0.008%

    No Known Activations