Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 16338
    Prev
    Next
    INDEX
    Explanations

    instances of the word "see" and its variations, indicating an emphasis on visual perception

    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
    soever
    -0.08
    fcn
    -0.08
    lero
    -0.07
    rok
    -0.07
    mx
    -0.07
    chine
    -0.07
     chá»ĭu
    -0.07
    lands
    -0.07
    (NO
    -0.06
    ly
    -0.06
    POSITIVE LOGITS
    attle
    0.09
    quential
    0.07
    ings
    0.07
    amp
    0.07
    ptic
    0.07
    ismo
    0.06
    è«
    0.06
    lected
    0.06
     cref
    0.06
    bastian
    0.06
    Activations Density 0.023%

    No Known Activations