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. 44398
    Prev
    Next
    INDEX
    Explanations

    the word "with" in various contexts and frequencies

    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
    gether
    -0.12
    ories
    -0.10
    pects
    -0.10
    oretical
    -0.10
    linear
    -0.09
    semblies
    -0.09
    anges
    -0.09
    ffects
    -0.08
    leep
    -0.08
    semble
    -0.08
    POSITIVE LOGITS
    standing
    0.14
    ered
    0.13
    ering
    0.13
    stood
    0.13
    eld
    0.12
    old
    0.12
    rawn
    0.12
    raw
    0.12
    dra
    0.12
    draw
    0.11
    Activations Density 0.012%

    No Known Activations