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. 43608
    Prev
    Next
    INDEX
    Explanations

    occurrences of the prefix "pro."

    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
    ullan
    -0.08
    m
    -0.08
    c
    -0.08
    cxx
    -0.08
    ry
    -0.07
    cq
    -0.07
    htags
    -0.07
    tik
    -0.07
    t
    -0.07
    morgan
    -0.07
    POSITIVE LOGITS
    s
    0.16
    vides
    0.15
    ceed
    0.15
    posed
    0.14
    vid
    0.14
    spect
    0.14
    tection
    0.13
    position
    0.13
    positions
    0.12
    ceeded
    0.12
    Activations Density 0.011%

    No Known Activations