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. 22-LLAMASCOPE-RES-131K
    6. 5771
    Prev
    Next
    INDEX
    Explanations

    terms related to assessments and selection processes in a formal context

    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
    ¸ı
    -0.06
    .edu
    -0.06
    tent
    -0.06
    utor
    -0.06
    oled
    -0.06
     Bureau
    -0.06
    glob
    -0.06
    uste
    -0.06
    uta
    -0.05
    ngo
    -0.05
    POSITIVE LOGITS
     club
    0.14
    club
    0.12
     Club
    0.11
    Club
    0.11
     clubhouse
    0.10
     clubs
    0.10
     CLUB
    0.09
    .club
    0.09
     committee
    0.09
    committee
    0.08
    Activations Density 0.028%

    No Known Activations