© 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. 129942
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "some" in various 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
    swer
    -0.08
    581
    -0.07
    unc
    -0.07
     fark
    -0.06
    ÑĢол
    -0.06
     bomb
    -0.06
     Morgan
    -0.06
    lah
    -0.06
    лий
    -0.06
    bes
    -0.06
    POSITIVE LOGITS
    ya
    0.07
    许
    0.07
    brero
    0.07
    emsp
    0.07
    weeney
    0.06
    ones
    0.06
    çī¹æ®Ĭ
    0.06
    plus
    0.06
    iyas
    0.06
    /all
    0.06
    Activations Density 0.036%

    No Known Activations