© 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. 86526
    Prev
    Next
    INDEX
    Explanations

    references to installing and playing a specific game on PC and mobile platforms

    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
    ime
    -0.06
     none
    -0.06
    adders
    -0.06
     PG
    -0.06
    igr
    -0.05
    illery
    -0.05
    ewise
    -0.05
    inal
    -0.05
     irre
    -0.05
    itos
    -0.05
    POSITIVE LOGITS
    BOSE
    0.08
    #
    0.08
    _marshall
    0.07
     initWithStyle
    0.07
    ücken
    0.07
    inke
    0.07
    acular
    0.07
    sko
    0.07
     surv
    0.07
    $MESS
    0.07
    Activations Density 0.002%

    No Known Activations