© 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. 119220
    Prev
    Next
    INDEX
    Explanations

    key concepts and significant statements

    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
     crib
    -0.07
     ÑĥÑģ
    -0.06
    illon
    -0.06
    oton
    -0.06
    unday
    -0.06
    ediator
    -0.06
    ucz
    -0.06
    plib
    -0.06
    adding
    -0.06
    اض
    -0.06
    POSITIVE LOGITS
    WithContext
    0.07
    ì¡°
    0.07
    rix
    0.07
    atri
    0.06
    brig
    0.06
    ÙĦاÙĤ
    0.06
    fa
    0.06
    coat
    0.06
    wire
    0.06
    .DrawLine
    0.06
    Activations Density 0.002%

    No Known Activations