© 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. 27316
    Prev
    Next
    INDEX
    Explanations

    actions and interactions involving physical objects

    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
    ickets
    -0.06
    resh
    -0.06
     Cre
    -0.06
    ĶĦ
    -0.06
    adv
    -0.06
    izard
    -0.06
    åde
    -0.06
     Tutorial
    -0.06
    propTypes
    -0.05
     eg
    -0.05
    POSITIVE LOGITS
    VERTISE
    0.07
    inya
    0.07
    είο
    0.07
    omination
    0.07
    ewis
    0.07
    ingo
    0.07
    lico
    0.07
    ãĥ¼ãĥ
    0.07
    :animated
    0.07
    roma
    0.07
    Activations Density 0.017%

    No Known Activations