© 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. 9-LLAMASCOPE-RES-131K
    11. 95662
    Prev
    Next
    INDEX
    Explanations

    geographical locations and geological features

    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
     noreferrer
    -0.07
    itto
    -0.06
    umm
    -0.06
    عة
    -0.06
    anten
    -0.06
    Rus
    -0.06
     tas
    -0.06
     Rural
    -0.06
    ROI
    -0.06
    eniz
    -0.06
    POSITIVE LOGITS
     addCriterion
    0.07
    ÃŃme
    0.07
    .onOptionsItemSelected
    0.07
    çļ
    0.06
    ÐIJÑĢÑħÑĸв
    0.06
    бÑĥдÑĮ
    0.06
    òng
    0.06
    .pg
    0.06
    composer
    0.06
    NST
    0.06
    Activations Density 0.026%

    No Known Activations