© 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 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. 29252
    Prev
    Next
    INDEX
    Explanations

    contractions and specific articles in conversational contexts

    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
    ÑĥÑģÑĤа
    -0.06
    uron
    -0.06
     Insider
    -0.06
    anova
    -0.06
    usr
    -0.06
    occo
    -0.06
    nd
    -0.06
    inne
    -0.06
    535
    -0.06
     Cout
    -0.06
    POSITIVE LOGITS
    ehir
    0.09
    Descriptors
    0.08
     tez
    0.07
     Alam
    0.06
     Shepard
    0.06
    anners
    0.06
    OrElse
    0.06
    ests
    0.06
    ált
    0.06
    à¤Łà¤ķ
    0.06
    Activations Density 0.051%

    No Known Activations