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. 44162
    Prev
    Next
    INDEX
    Explanations

    symbols and terms related to analysis and metrics in scientific contexts

    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
    CKER
    -0.07
    ilde
    -0.06
    cker
    -0.06
     zg
    -0.06
     tariffs
    -0.06
    ondo
    -0.06
    uzzi
    -0.06
    üb
    -0.06
    zier
    -0.06
    ÑĤап
    -0.06
    POSITIVE LOGITS
     fraud
    0.12
     SSA
    0.11
     Fraud
    0.11
    fra
    0.10
     fraudulent
    0.10
    Fra
    0.09
     Social
    0.09
     Welfare
    0.09
     improper
    0.09
     program
    0.09
    Activations Density 0.016%

    No Known Activations