© 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. 54576
    Prev
    Next
    INDEX
    Explanations

    terms related to endings or conclusions

    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
    wiÄħ
    -0.09
    eydi
    -0.08
     lesbi
    -0.07
     ÑĢеÑģ
    -0.07
    iazza
    -0.07
    batim
    -0.07
    imdi
    -0.07
     svaz
    -0.07
    ÑĢÑĸп
    -0.07
    ÑħÑĥ
    -0.07
    POSITIVE LOGITS
     aff
    0.06
    ennen
    0.05
    ednou
    0.05
    ,
    0.05
     remember
    0.05
    idden
    0.05
    cox
    0.05
     foc
    0.05
    寸
    0.05
    Ì
    0.05
    Activations Density 0.000%

    No Known Activations