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. 9-LLAMASCOPE-RES-131K
    6. 96182
    Prev
    Next
    INDEX
    Explanations

    references to various types of fasteners and construction materials

    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
    emme
    -0.07
    ÑĢÑıдÑĥ
    -0.07
    elper
    -0.07
    paging
    -0.07
    inka
    -0.07
    .Names
    -0.06
    θε
    -0.06
    pager
    -0.06
    vou
    -0.06
     Phelps
    -0.06
    POSITIVE LOGITS
    imat
    0.07
    atore
    0.07
    itar
    0.06
    ik
    0.06
    å¥
    0.06
    ion
    0.06
    iat
    0.06
    åĽ½äº§
    0.06
    _GENER
    0.06
    asant
    0.06
    Activations Density 0.004%

    No Known Activations