© 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. 60200
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and text structure indicative of opinions or assertions

    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
    mand
    -0.07
    weetalert
    -0.07
    изнеÑģ
    -0.06
    roperty
    -0.06
     Cone
    -0.06
    ocos
    -0.06
     Bair
    -0.06
    .ExecuteReader
    -0.06
    amina
    -0.06
    ouncer
    -0.06
    POSITIVE LOGITS
     nor
    0.15
    nor
    0.13
     Nor
    0.11
    Nor
    0.09
     NOR
    0.08
     neither
    0.08
     contrary
    0.07
     anymore
    0.07
    尽管
    0.07
    LEC
    0.06
    Activations Density 0.036%

    No Known Activations