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. 11517
    Prev
    Next
    INDEX
    Explanations

    references to historical events, particularly conflicts and wars

    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
    enal
    -0.07
    _flutter
    -0.07
     FEATURE
    -0.07
     nod
    -0.07
    Ïħγ
    -0.06
     LENG
    -0.06
    07
    -0.06
    iable
    -0.06
    5
    -0.06
    ÑĢÑĥкÑĤ
    -0.06
    POSITIVE LOGITS
     
    0.09
    102
    0.07
    194
    0.06
    180
    0.06
     Nah
    0.06
    195
    0.06
    149
    0.06
    lexport
    0.06
    puties
    0.06
    249
    0.06
    Activations Density 0.015%

    No Known Activations