© 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. 60397
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate conditions and constraints in mathematical definitions or propositions

    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
    hari
    -0.07
    ÑĢоÑİ
    -0.07
    lab
    -0.07
    ng
    -0.06
    acket
    -0.06
    код
    -0.06
    alse
    -0.06
    inn
    -0.06
     Dodd
    -0.05
    ÑĢоÑģÑĤо
    -0.05
    POSITIVE LOGITS
     hence
    0.08
    kus
    0.08
    бо
    0.07
    /or
    0.07
    /OR
    0.07
    Fade
    0.07
    #w
    0.07
    ulo
    0.07
    REFERRED
    0.07
    .generated
    0.07
    Activations Density 0.141%

    No Known Activations