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. 11452
    Prev
    Next
    INDEX
    Explanations

    references to specific policies and procedures, particularly those related to school and administrative matters

    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
    elder
    -0.06
     [â̦]↵
    -0.05
    Âł↵
    -0.05
    ismet
    -0.05
    ør
    -0.05
    roje
    -0.05
     zero
    -0.05
    emy
    -0.05
    IntegerField
    -0.05
     â̦↵
    -0.05
    POSITIVE LOGITS
    .
    0.16
    à¥Ģ.
    0.09
    .$.
    0.08
    à¥ĩ.
    0.08
    ा.
    0.08
    .:.:.
    0.07
    .:.:.:.
    0.07
    ãĥĩãĤ£ãĤ¢
    0.07
    .@
    0.07
     thôi
    0.07
    Activations Density 0.038%

    No Known Activations