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. 43592
    Prev
    Next
    INDEX
    Explanations

    mentions of San Francisco and its associated institutions or events

    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
    chein
    -0.07
    ÑĥлÑİ
    -0.07
    usted
    -0.07
    ieee
    -0.07
    ices
    -0.07
    agal
    -0.07
    füh
    -0.07
    ailed
    -0.07
    word
    -0.06
    ffi
    -0.06
    POSITIVE LOGITS
     Chronicle
    0.13
     Bay
    0.12
     Giants
    0.12
     bay
    0.10
     Mime
    0.10
     Examiner
    0.10
    Chron
    0.09
     Unified
    0.09
     Peninsula
    0.09
     Chron
    0.09
    Activations Density 0.010%

    No Known Activations