© 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. 30777
    Prev
    Next
    INDEX
    Explanations

    actions related to collisions or encounters

    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
    adr
    -0.08
    fare
    -0.06
    ulong
    -0.06
    onda
    -0.06
     comprom
    -0.06
    tran
    -0.06
    oger
    -0.06
    нÑĮ
    -0.06
    \Framework
    -0.06
    idor
    -0.06
    POSITIVE LOGITS
     wall
    0.07
    wall
    0.07
    %A
    0.07
    å£ģ
    0.07
    ì¹
    0.07
     brick
    0.07
    ONTAL
    0.07
     Dip
    0.06
    brick
    0.06
    =post
    0.06
    Activations Density 0.033%

    No Known Activations