© 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. 701
    Prev
    Next
    INDEX
    Explanations

    HTML elements related to navigation and text content structure

    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
    owie
    -0.07
    ritel
    -0.07
    anes
    -0.07
    afort
    -0.07
    lig
    -0.07
    crete
    -0.07
    ages
    -0.07
    δο
    -0.07
    ords
    -0.07
    uft
    -0.07
    POSITIVE LOGITS
    /MIT
    0.06
     Wendy
    0.06
    ãĤĪãģĨ
    0.06
     Meredith
    0.06
    izr
    0.06
    ì¸ł
    0.06
    icable
    0.05
    zure
    0.05
     text
    0.05
    edException
    0.05
    Activations Density 0.000%

    No Known Activations