© 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. 39600
    Prev
    Next
    INDEX
    Explanations

    specific temporal references and incidents

    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
    asper
    -0.07
    abaj
    -0.07
    âng
    -0.06
    //{{
    -0.06
    ãĥ¼ãĥį
    -0.06
    ottes
    -0.06
    å¾®ç¬ij
    -0.06
    .ns
    -0.06
    ailable
    -0.06
    ãĤ«ãĥĨ
    -0.06
    POSITIVE LOGITS
    utr
    0.07
    ito
    0.06
    apsed
    0.06
    Sau
    0.06
     Merkel
    0.06
    tru
    0.06
    ÎķÎ¥
    0.06
    getInstance
    0.06
     Sau
    0.06
     ÑĢайоне
    0.06
    Activations Density 0.022%

    No Known Activations