© 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. 38962
    Prev
    Next
    INDEX
    Explanations

    references to body parts and their positions

    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
    egov
    -0.07
    åĻ¨
    -0.06
    .crm
    -0.06
     åĶ
    -0.06
    apa
    -0.06
    ixe
    -0.06
    loquent
    -0.06
    uilt
    -0.06
    ucc
    -0.06
    ró
    -0.06
    POSITIVE LOGITS
    /back
    0.11
    (back
    0.09
    .Back
    0.08
    back
    0.08
    /front
    0.08
    -back
    0.07
    side
    0.07
     backs
    0.07
    matter
    0.07
    ward
    0.06
    Activations Density 0.011%

    No Known Activations