© 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. 107472
    Prev
    Next
    INDEX
    Explanations

    instances of a specific character or symbol

    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
    íļ¨
    -0.07
    Ñģим
    -0.07
    ÑĨеп
    -0.07
    ÙĨداÙĨ
    -0.07
    ities
    -0.07
    izin
    -0.07
     ÙĦدÙĬ
    -0.07
    Ư
    -0.07
    fans
    -0.07
    oller
    -0.07
    POSITIVE LOGITS
    uers
    0.06
     Continue
    0.06
    lest
    0.06
    untu
    0.06
    Continue
    0.06
    itus
    0.06
    eld
    0.06
     continue
    0.05
    ehr
    0.05
    put
    0.05
    Activations Density 0.008%

    No Known Activations