© 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. 62099
    Prev
    Next
    INDEX
    Explanations

    questions starting with "where" related to location and context

    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
     Christ
    -0.06
    akash
    -0.06
    elah
    -0.06
    vÄĽ
    -0.06
    ERGE
    -0.06
    tracker
    -0.06
    zin
    -0.06
     Principle
    -0.06
    theon
    -0.06
     Pou
    -0.06
    POSITIVE LOGITS
    $MESS
    0.09
    ÙĬاÙĨ
    0.07
    uteur
    0.06
    oom
    0.06
     Ferd
    0.06
     Herman
    0.06
    anic
    0.06
    ̣
    0.06
    aten
    0.06
    oya
    0.06
    Activations Density 0.042%

    No Known Activations