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. MLP Out
    5. 25-LLAMASCOPE-MLP-131K
    6. 72551
    Prev
    Next
    INDEX
    Explanations

    text related to identity and legal classifications

    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
    mac
    -0.06
    kr
    -0.06
    ugo
    -0.06
    610
    -0.06
    opa
    -0.06
    ya
    -0.06
    icle
    -0.06
    опиÑģ
    -0.06
     Zero
    -0.06
    611
    -0.06
    POSITIVE LOGITS
    omi
    0.08
    .mixin
    0.07
    rowse
    0.07
    ÑĥлÑİ
    0.07
     Couch
    0.07
    omba
    0.07
    ëį°
    0.07
    ombs
    0.06
    dux
    0.06
    è°±
    0.06
    Activations Density 0.193%

    No Known Activations