© 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. 72107
    Prev
    Next
    INDEX
    Explanations

    references to food, calories, and cultural critiques

    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
    emens
    -0.08
    caster
    -0.08
    idor
    -0.07
    NotAllowed
    -0.07
    abilia
    -0.07
    redients
    -0.07
    ampion
    -0.07
    ToWorld
    -0.07
    à¸Ĺย
    -0.07
    rapper
    -0.07
    POSITIVE LOGITS
     altogether
    0.10
     forget
    0.08
    ari
    0.07
     Forget
    0.06
    !
    0.06
    io
    0.06
    Forget
    0.06
     entirely
    0.06
     defer
    0.06
    bout
    0.05
    Activations Density 0.013%

    No Known Activations