© 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. 61722
    Prev
    Next
    INDEX
    Explanations

    numerical values and specific quantifiable data

    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
    levator
    -0.07
    ycz
    -0.07
    empo
    -0.07
    itez
    -0.07
    epad
    -0.07
    emes
    -0.07
    dato
    -0.07
    ulary
    -0.06
    .ua
    -0.06
    illard
    -0.06
    POSITIVE LOGITS
     Chevron
    0.06
    ye
    0.06
    090
    0.06
     à¤Ķ
    0.05
    098
    0.05
    097
    0.05
    095
    0.05
    ãĤ¥
    0.05
     Lightning
    0.05
    itm
    0.05
    Activations Density 0.002%

    No Known Activations