© 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. 106626
    Prev
    Next
    INDEX
    Explanations

    key phrases related to submission processes and expectations

    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
    ả
    -0.07
    unker
    -0.07
    euillez
    -0.06
    oden
    -0.06
    rial
    -0.06
    ãģ²ãģ¨
    -0.06
    inky
    -0.06
    ombat
    -0.06
    combe
    -0.06
     base
    -0.06
    POSITIVE LOGITS
    isure
    0.07
    Scrollbar
    0.07
    ara
    0.06
    WSC
    0.06
    .Throw
    0.06
    _TM
    0.06
    ä»ĭ
    0.06
    isc
    0.06
    ropa
    0.06
    ecure
    0.06
    Activations Density 0.000%

    No Known Activations