© 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. 120237
    Prev
    Next
    INDEX
    Explanations

    technical terms and keywords related to application headers and response contexts in 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
    zig
    -0.07
    ÌĨ
    -0.07
    ÃŃl
    -0.07
    erg
    -0.06
    less
    -0.06
    fully
    -0.06
    ová
    -0.06
    ane
    -0.06
    null
    -0.06
    he
    -0.06
    POSITIVE LOGITS
    'S
    0.09
    ’S
    0.09
     Kaynak
    0.07
    uniacid
    0.07
    vider
    0.07
    IS
    0.07
    Ä°
    0.07
    taboola
    0.07
    modifiable
    0.07
    activex
    0.07
    Activations Density 0.345%

    No Known Activations