© 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. 61786
    Prev
    Next
    INDEX
    Explanations

    negations or phrases expressing doubt

    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
    vÄĽt
    -0.07
     é¡
    -0.07
    itore
    -0.06
    å¯Ŀ
    -0.06
    .centerX
    -0.06
    otec
    -0.06
    undance
    -0.06
    utt
    -0.06
    anus
    -0.06
     caul
    -0.06
    POSITIVE LOGITS
     even
    0.08
     anymore
    0.07
     least
    0.07
     unless
    0.07
     Jah
    0.07
    ICS
    0.06
    withstanding
    0.06
    epad
    0.06
    icing
    0.06
    /net
    0.06
    Activations Density 0.009%

    No Known Activations