© 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. 54150
    Prev
    Next
    INDEX
    Explanations

    references to summer experiences and community bonding at camp

    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
     late
    -0.07
     early
    -0.07
     earliest
    -0.06
    olidays
    -0.06
    plx
    -0.06
    á»±c
    -0.06
    wer
    -0.05
     Sylv
    -0.05
     initial
    -0.05
    vey
    -0.05
    POSITIVE LOGITS
     fours
    0.08
    ä¸īå¹´
    0.07
    actable
    0.07
     dört
    0.07
     ЧеÑĢез
    0.07
    )frame
    0.07
     six
    0.07
    tone
    0.07
     four
    0.07
    íĥĦ
    0.07
    Activations Density 0.053%

    No Known Activations