© 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. 98159
    Prev
    Next
    INDEX
    Explanations

    phrases indicating collaboration or partnership

    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
    etten
    -0.08
    uren
    -0.08
    antal
    -0.07
    hiba
    -0.07
    hoff
    -0.07
    Value
    -0.07
    ovel
    -0.06
    adece
    -0.06
    816
    -0.06
    ufen
    -0.06
    POSITIVE LOGITS
     regard
    0.16
     regards
    0.14
    stood
    0.14
     nhau
    0.13
    standing
    0.12
    /by
    0.12
     respect
    0.11
    holds
    0.10
    olding
    0.10
    drawing
    0.10
    Activations Density 0.482%

    No Known Activations