Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5442
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and structured elements in text

    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
     jedem
    -0.07
    specialchars
    -0.06
    asl
    -0.06
    efore
    -0.06
    gles
    -0.06
    olas
    -0.06
    YP
    -0.06
    ême
    -0.06
     célib
    -0.06
    há
    -0.06
    POSITIVE LOGITS
    ãģĻãĤĭãģ¨
    0.10
     wait
    0.08
    wait
    0.08
    vo
    0.08
     Prest
    0.08
     Wait
    0.07
     then
    0.07
     vo
    0.07
     Doing
    0.07
    Wait
    0.07
    Activations Density 0.016%

    No Known Activations