© 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. 104521
    Prev
    Next
    INDEX
    Explanations

    references to specific policies and ethical guidelines associated with an organization

    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
    qv
    -0.07
    ãĥ¼ãĥĸãĥ«
    -0.07
    üc
    -0.07
    epad
    -0.07
    indow
    -0.06
    ogo
    -0.06
    .Sdk
    -0.06
    ely
    -0.06
    ahn
    -0.06
    ammable
    -0.06
    POSITIVE LOGITS
    onian
    0.07
    onor
    0.06
     Wich
    0.06
     Wend
    0.06
     datap
    0.06
    éģ
    0.06
    ropol
    0.06
    earer
    0.06
     ships
    0.06
    stadt
    0.06
    Activations Density 0.003%

    No Known Activations