© 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. 92722
    Prev
    Next
    INDEX
    Explanations

    components of programming or coding 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
    она
    -0.06
    帰
    -0.06
    emas
    -0.06
    oid
    -0.06
    ondon
    -0.06
    /all
    -0.06
    visor
    -0.06
    ondo
    -0.06
    rypt
    -0.06
    erty
    -0.06
    POSITIVE LOGITS
    )(↵
    0.08
    è¡
    0.07
    تÙĦ
    0.07
    indow
    0.07
    miner
    0.07
    abra
    0.06
    _bases
    0.06
    LARI
    0.06
    wit
    0.06
    venues
    0.06
    Activations Density 0.009%

    No Known Activations