© 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. 107781
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Tar" or related terms in films and discussions about them

    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
     Phelps
    -0.07
    oft
    -0.07
    _tE
    -0.07
    _firestore
    -0.06
    izer
    -0.06
    uales
    -0.06
    xeb
    -0.06
    ote
    -0.06
    elho
    -0.06
    orf
    -0.06
    POSITIVE LOGITS
    agram
    0.07
     Civ
    0.06
    üns
    0.06
    atak
    0.06
    entine
    0.06
    leigh
    0.06
     Nicholson
    0.06
    uns
    0.06
    raz
    0.06
     Trouble
    0.06
    Activations Density 0.008%

    No Known Activations