© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 90191
    Prev
    Next
    INDEX
    Explanations

    discussions around socio-economic issues and community resource allocation

    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
    .Localization
    -0.07
    reactstrap
    -0.06
    atform
    -0.06
    stoup
    -0.06
    rame
    -0.06
    retval
    -0.06
    ÄĽji
    -0.06
    iminal
    -0.06
    inals
    -0.06
    ̧
    -0.06
    POSITIVE LOGITS
     Trot
    0.07
     patterns
    0.06
     magnets
    0.06
     Patterns
    0.06
    icker
    0.06
    patterns
    0.06
    asd
    0.06
    .Encoding
    0.06
     school
    0.05
     schools
    0.05
    Activations Density 0.004%

    No Known Activations