© 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. 74041
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "им" which could indicate possession or relatedness in the context

    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
    encing
    -0.09
    ìĿ
    -0.08
    ENO
    -0.08
    ÑģÑĤÑİ
    -0.07
    ,âĢ¦↵↵
    -0.07
    WithMany
    -0.07
    .gdx
    -0.07
    assa
    -0.07
    еннÑĸ
    -0.07
     Ú¯ÛĮر
    -0.07
    POSITIVE LOGITS
     limb
    0.07
     Mall
    0.06
     notes
    0.06
    s
    0.06
    Ñĥл
    0.06
     Kauf
    0.06
    cron
    0.06
     cron
    0.06
     Tender
    0.05
    ¼
    0.05
    Activations Density 0.001%

    No Known Activations