© 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 EvalsExportsAPI 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. 130208
    Prev
    Next
    INDEX
    Explanations

    locations or settings that evoke strong emotional or existential themes

    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
    Ñģол
    -0.08
    ноÑģ
    -0.08
    hari
    -0.08
     trao
    -0.08
     GANG
    -0.07
    apphire
    -0.07
    porte
    -0.07
    rien
    -0.07
    Ñģен
    -0.07
    entai
    -0.07
    POSITIVE LOGITS
     where
    0.12
     place
    0.10
    where
    0.09
     places
    0.09
     Where
    0.08
     donde
    0.08
     frequ
    0.08
    Where
    0.08
     location
    0.08
     site
    0.07
    Activations Density 0.035%

    No Known Activations