© 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. 124793
    Prev
    Next
    INDEX
    Explanations

    expressions related to accountability in environmental actions

    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
     '
    -0.06
     occ
    -0.06
     "
    -0.06
     [âĢ¦]
    -0.06
    rod
    -0.06
     Gel
    -0.05
     Ec
    -0.05
    "
    -0.05
    âĢ¦
    -0.05
     [=
    -0.05
    POSITIVE LOGITS
     Erotische
    0.08
    addir
    0.08
    ymm
    0.08
    raÄį
    0.08
    Ãłnh
    0.07
    liš
    0.07
    år
    0.07
    uitka
    0.07
    iversit
    0.07
    ehr
    0.07
    Activations Density 0.034%

    No Known Activations