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. 44357
    Prev
    Next
    INDEX
    Explanations

    phrases related to planning and organization

    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
    .easing
    -0.06
    èŃī
    -0.06
     CONTRIBUTORS
    -0.06
    oria
    -0.06
    зи
    -0.06
    ROLS
    -0.06
    епÑĤи
    -0.06
     عرض
    -0.06
    ì§Ī
    -0.06
    .Buttons
    -0.06
    POSITIVE LOGITS
     jot
    0.12
     write
    0.11
     pencil
    0.11
     scri
    0.11
     WRITE
    0.10
     Write
    0.10
     map
    0.10
     writing
    0.10
     list
    0.10
     penc
    0.09
    Activations Density 0.027%

    No Known Activations