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. 43490
    Prev
    Next
    INDEX
    Explanations

    URLs and domain names

    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
    bio
    -0.10
    ois
    -0.08
    boo
    -0.08
    ses
    -0.08
    stu
    -0.08
    rese
    -0.08
    oa
    -0.08
    yo
    -0.07
    phony
    -0.07
    idian
    -0.07
    POSITIVE LOGITS
    .uk
    0.14
    .za
    0.09
    .tt
    0.09
    .nz
    0.09
    ypress
    0.08
    op
    0.08
    yle
    0.08
    erview
    0.08
    otten
    0.08
    ût
    0.08
    Activations Density 0.005%

    No Known Activations