© 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. 107947
    Prev
    Next
    INDEX
    Explanations

    conditional statements involving possible scenarios or outcomes

    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
    pite
    -0.07
    ردÙĩ
    -0.07
    inet
    -0.07
    upal
    -0.07
    ần
    -0.07
    izza
    -0.07
    ôle
    -0.07
    AGON
    -0.07
    ials
    -0.07
    .$.
    -0.07
    POSITIVE LOGITS
     every
    0.07
    uru
    0.06
     conserv
    0.06
     somehow
    0.06
     hät
    0.06
     each
    0.06
     instead
    0.06
    less
    0.06
     full
    0.06
     ap
    0.05
    Activations Density 0.020%

    No Known Activations