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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 31-LLAMASCOPE-RES-131K
    6. 44285
    Prev
    Next
    INDEX
    Explanations

    words associated with radical ideas or movements

    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
    ListGroup
    -0.07
     Christina
    -0.06
    BD
    -0.06
    iya
    -0.06
     dok
    -0.06
    i
    -0.06
     Coast
    -0.06
    dül
    -0.06
    eer
    -0.06
    zell
    -0.06
    POSITIVE LOGITS
    ium
    0.14
    iances
    0.12
    ially
    0.11
    iao
    0.10
    ars
    0.10
    ials
    0.10
    ion
    0.10
    mium
    0.09
    ian
    0.09
    iais
    0.09
    Activations Density 0.005%

    No Known Activations