© 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. 54319
    Prev
    Next
    INDEX
    Explanations

    phrases related to manipulation and cover-ups in political contexts

    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
    bonus
    -0.07
    peÄį
    -0.07
    orge
    -0.06
    offer
    -0.06
    ênh
    -0.06
    à¸Ńล
    -0.06
     jemand
    -0.06
    .utility
    -0.06
    èĽĩ
    -0.06
    pose
    -0.06
    POSITIVE LOGITS
     fact
    0.09
     reality
    0.09
     otherwise
    0.09
     realities
    0.08
     real
    0.07
     realidad
    0.07
     facts
    0.07
     Pon
    0.07
     reveal
    0.07
     truth
    0.07
    Activations Density 0.027%

    No Known Activations