© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 105743
    Prev
    Next
    INDEX
    Explanations

    punctuation marks related to queries, particularly question marks

    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
    ¹
    -0.06
    ickers
    -0.05
    icked
    -0.05
     Feld
    -0.05
    âĢ¦
    -0.05
    fk
    -0.05
    azzo
    -0.05
    ami
    -0.05
    772
    -0.05
    rms
    -0.05
    POSITIVE LOGITS
    jac
    0.09
    arrera
    0.07
    olib
    0.07
    Ľå»º
    0.07
    inf
    0.07
    \Block
    0.07
    corner
    0.07
    ÑĤÑĢон
    0.07
    aklı
    0.07
    ÐĬ
    0.07
    Activations Density 0.000%

    No Known Activations