© 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. 15331
    Prev
    Next
    INDEX
    Explanations

    interactions or questions directed at the audience

    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
     feedback
    -0.07
    /feed
    -0.07
     MouseButton
    -0.07
    .feedback
    -0.07
    resent
    -0.06
    ((&
    -0.06
     Feedback
    -0.06
    Reviewed
    -0.06
    ì²ł
    -0.06
     Keystone
    -0.06
    POSITIVE LOGITS
     picks
    0.08
     Desert
    0.07
     reveal
    0.06
     Mine
    0.06
     favorite
    0.06
    åĽŀçŃĶ
    0.06
    enne
    0.06
     lists
    0.06
     answer
    0.06
     favourite
    0.06
    Activations Density 0.046%

    No Known Activations