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. 22-LLAMASCOPE-RES-131K
    6. 5706
    Prev
    Next
    INDEX
    Explanations

    expressions of personal identity and self-perception

    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
    uD
    -0.09
    ospel
    -0.07
    obe
    -0.06
    uger
    -0.06
    erialize
    -0.06
    angan
    -0.06
    ãĥ¼ãĥĵ
    -0.06
    oco
    -0.06
    fabs
    -0.06
    ledge
    -0.06
    POSITIVE LOGITS
     someone
    0.09
     somebody
    0.08
     neither
    0.08
     fortunate
    0.08
     lucky
    0.08
     unusual
    0.07
    eyin
    0.07
     luck
    0.07
    someone
    0.07
     currently
    0.07
    Activations Density 0.040%

    No Known Activations