© 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. 41542
    Prev
    Next
    INDEX
    Explanations

    expressions indicating existence or state of being

    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
    380
    -0.08
    288
    -0.07
    068
    -0.07
    oop
    -0.07
    580
    -0.06
    Ñĩин
    -0.06
    460
    -0.06
    TTY
    -0.06
    240
    -0.06
    offee
    -0.06
    POSITIVE LOGITS
     now
    0.08
    oro
    0.07
     hereby
    0.07
     down
    0.07
    now
    0.06
     starting
    0.06
    onna
    0.06
     ramp
    0.06
    anda
    0.06
     still
    0.06
    Activations Density 0.036%

    No Known Activations