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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5241
    Prev
    Next
    INDEX
    Explanations

    CSS properties and their values

    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
    loff
    -0.07
    727
    -0.06
     Pep
    -0.06
    incer
    -0.06
    HeaderValue
    -0.06
    ÏħÏĩ
    -0.06
    PasswordField
    -0.06
    ntl
    -0.06
     tbody
    -0.05
    à¤Ĺल
    -0.05
    POSITIVE LOGITS
    rounded
    0.09
    _ROUND
    0.08
     borderRadius
    0.08
    Round
    0.08
     Round
    0.08
     box
    0.07
     rounding
    0.07
    arden
    0.07
    uran
    0.07
     border
    0.07
    Activations Density 0.019%

    No Known Activations