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. 43562
    Prev
    Next
    INDEX
    Explanations

    references to government agencies and formal reports

    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
     AFL
    -0.08
    olars
    -0.06
    adients
    -0.06
     صاØŃب
    -0.06
    battery
    -0.06
    /antlr
    -0.06
    ndern
    -0.06
    abay
    -0.06
     zmq
    -0.06
    ë°ĶìĿ´
    -0.06
    POSITIVE LOGITS
     Cabinet
    0.12
     Civil
    0.11
     minister
    0.11
     taxpayer
    0.11
     gov
    0.10
     ministers
    0.10
    .gov
    0.10
     civil
    0.10
     government
    0.10
     departments
    0.10
    Activations Density 0.008%

    No Known Activations