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. 96140
    Prev
    Next
    INDEX
    Explanations

    terms related to communication hardware and technology, particularly speakerphones and their functionalities

    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
    regnum
    -0.06
    foon
    -0.06
    thouse
    -0.06
    ungan
    -0.06
    usto
    -0.06
    erne
    -0.06
    culos
    -0.05
     Sesso
    -0.05
    oust
    -0.05
     tart
    -0.05
    POSITIVE LOGITS
    .syntax
    0.07
    MLE
    0.07
     Plane
    0.07
    krom
    0.07
    -plane
    0.07
    ept
    0.07
    ToPoint
    0.07
     Raq
    0.06
    chio
    0.06
    BSD
    0.06
    Activations Density 0.103%

    No Known Activations