© 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. 70274
    Prev
    Next
    INDEX
    Explanations

    references to perception and interpretation of reality

    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
    bang
    -0.06
    سط
    -0.06
     Verde
    -0.06
    thy
    -0.06
     Tits
    -0.06
    ears
    -0.06
    apphire
    -0.06
    ovah
    -0.06
    repair
    -0.06
    aty
    -0.06
    POSITIVE LOGITS
     significance
    0.08
     mote
    0.07
    YNC
    0.07
     conspir
    0.07
    alam
    0.06
    ossal
    0.06
    angle
    0.06
    iyon
    0.06
     meanings
    0.06
    uras
    0.06
    Activations Density 0.069%

    No Known Activations