© 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. 9-LLAMASCOPE-RES-131K
    11. 95433
    Prev
    Next
    INDEX
    Explanations

    file path or code syntax related to programming

    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
    onders
    -0.06
    ands
    -0.06
     trif
    -0.06
    Äĥng
    -0.06
     ticker
    -0.05
    oo
    -0.05
    emoc
    -0.05
     Lal
    -0.05
     conf
    -0.05
    èĢĮ
    -0.05
    POSITIVE LOGITS
    enville
    0.09
    ropri
    0.07
     Zuk
    0.07
    ruž
    0.07
    غÙĬÙĦ
    0.07
    .xr
    0.07
    NECT
    0.07
    ORA
    0.07
     Dash
    0.07
    azio
    0.07
    Activations Density 0.000%

    No Known Activations