© 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. 39317
    Prev
    Next
    INDEX
    Explanations

    themes of struggle and advocacy for freedom and women's rights

    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
    î
    -0.07
    apl
    -0.07
    olicit
    -0.06
     Fif
    -0.06
    amedi
    -0.06
    çŃĭ
    -0.06
     chez
    -0.06
    วà¸Ļ
    -0.06
    resi
    -0.06
    glich
    -0.06
    POSITIVE LOGITS
     predecessors
    0.08
     generation
    0.08
     generations
    0.07
     sacrifices
    0.07
     ancestors
    0.07
    -actions
    0.07
    .Today
    0.07
    алов
    0.06
    eme
    0.06
     decades
    0.06
    Activations Density 0.025%

    No Known Activations