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. 5404
    Prev
    Next
    INDEX
    Explanations

    pronouns associated with individuals and their relationships

    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
    elman
    -0.08
    iliz
    -0.08
    bout
    -0.07
    ppo
    -0.07
    dio
    -0.07
    rides
    -0.07
    dna
    -0.07
    tails
    -0.07
    elan
    -0.07
    lectron
    -0.07
    POSITIVE LOGITS
     into
    0.13
     astr
    0.12
     to
    0.11
     toward
    0.10
     away
    0.10
     towards
    0.10
     nowhere
    0.09
     onto
    0.08
     Into
    0.08
    into
    0.08
    Activations Density 0.008%

    No Known Activations