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. 43777
    Prev
    Next
    INDEX
    Explanations

    inconsistencies and errors in spelling or word forms

    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
     McGu
    -0.06
     Bian
    -0.06
    ĥ
    -0.06
    chai
    -0.06
    oded
    -0.06
    oit
    -0.06
    ausible
    -0.06
    AMENT
    -0.06
    etheus
    -0.06
    uxe
    -0.06
    POSITIVE LOGITS
    roscope
    0.14
    ula
    0.11
    ration
    0.10
    ergy
    0.10
    org
    0.10
    proc
    0.09
    enes
    0.09
    ppo
    0.09
    imes
    0.09
    bson
    0.09
    Activations Density 0.004%

    No Known Activations