© 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. 107412
    Prev
    Next
    INDEX
    Explanations

    sections labeled "Introduction" and "Conclusion" in documents

    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
    iggs
    -0.07
    emes
    -0.07
    mtree
    -0.07
    pery
    -0.06
    ÑĮко
    -0.06
    ungalow
    -0.06
    ourn
    -0.06
    ุà¸Ķà¸Ĺ
    -0.06
     moderation
    -0.06
    exit
    -0.06
    POSITIVE LOGITS
    ASA
    0.06
    ERA
    0.06
    )did
    0.06
    /AFP
    0.06
    erah
    0.06
    ANI
    0.06
     Barker
    0.06
    ĥ
    0.05
    RIA
    0.05
    fad
    0.05
    Activations Density 0.009%

    No Known Activations