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. 5710
    Prev
    Next
    INDEX
    Explanations

    terms related to psychological analysis and academic discourse

    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
    iversit
    -0.07
    né
    -0.06
    寸
    -0.06
    ëį°ìĿ´íĬ¸
    -0.06
    opup
    -0.06
    enga
    -0.06
    utherland
    -0.06
     Barcl
    -0.06
    öt
    -0.06
     vin
    -0.06
    POSITIVE LOGITS
    íĥģ
    0.06
    orrow
    0.06
    MI
    0.06
    åĽ½äº§
    0.06
    lien
    0.06
    eward
    0.06
    gili
    0.06
    ODO
    0.06
    380
    0.06
    496
    0.06
    Activations Density 0.000%

    No Known Activations