© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 61699
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing certainty or precision in statements

    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
    isma
    -0.07
    azu
    -0.07
    ange
    -0.07
    fant
    -0.07
    oret
    -0.07
    actionDate
    -0.07
    Chance
    -0.07
    339
    -0.06
    umba
    -0.06
    ngine
    -0.06
    POSITIVE LOGITS
    agle
    0.07
    czy
    0.07
    iyat
    0.06
    ên
    0.06
     spell
    0.06
     iv
    0.06
    enes
    0.06
     Tet
    0.06
    ENA
    0.06
    icina
    0.06
    Activations Density 0.004%

    No Known Activations