© 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. 107897
    Prev
    Next
    INDEX
    Explanations

    time indicators and scheduling information

    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
    okol
    -0.06
    ichert
    -0.06
    reten
    -0.06
    ills
    -0.06
    ilihan
    -0.06
    oids
    -0.06
    kek
    -0.06
     hat
    -0.06
    ostel
    -0.06
    978
    -0.05
    POSITIVE LOGITS
    itmap
    0.07
    ساب
    0.07
     rowspan
    0.07
    ãĥĵãĥ¼
    0.07
    raquo
    0.07
     ï½ľ
    0.06
     ìĸ¼
    0.06
    covered
    0.06
    MITTED
    0.06
    è¼Ŀ
    0.06
    Activations Density 0.002%

    No Known Activations