© 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. 107559
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals, places, or entities

    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
    éĹ
    -0.07
    laps
    -0.07
    efeller
    -0.07
    conti
    -0.07
     Bulk
    -0.07
    лиж
    -0.07
    bjerg
    -0.06
    arpa
    -0.06
     Rarity
    -0.06
    chner
    -0.06
    POSITIVE LOGITS
    еÐ
    0.08
    âĢª
    0.07
    hh
    0.07
    Ìģ
    0.07
    ¬
    0.07
    łéĻ¤
    0.06
    (er
    0.06
    inge
    0.06
     Sexy
    0.06
    steam
    0.06
    Activations Density 0.194%

    No Known Activations