© 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 EvalsExportsAPI 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. 29171
    Prev
    Next
    INDEX
    Explanations

    variations of the word "head" in different contexts, particularly related to movement or direction

    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
    oday
    -0.07
    amax
    -0.07
    δα
    -0.06
    anager
    -0.06
    pit
    -0.06
    rides
    -0.06
     mã
    -0.06
    173
    -0.06
    sonian
    -0.06
     Marr
    -0.06
    POSITIVE LOGITS
    lined
    0.09
    lining
    0.09
    BD
    0.07
    ilty
    0.07
    arella
    0.07
    ecimal
    0.07
    itar
    0.06
     towards
    0.06
    liner
    0.06
    ivet
    0.06
    Activations Density 0.010%

    No Known Activations