© 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. 17-LLAMASCOPE-RES-131K
    11. 87209
    Prev
    Next
    INDEX
    Explanations

    country names and geographic locations

    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
     trim
    -0.06
    reas
    -0.06
     пÑĢи
    -0.06
    ued
    -0.05
     super
    -0.05
     thus
    -0.05
    [OF
    -0.05
    .getBounds
    -0.05
     bird
    -0.05
     re
    -0.05
    POSITIVE LOGITS
    _mD
    0.08
    lán
    0.08
    _Tis
    0.07
    ÃŃna
    0.07
    ë°°
    0.07
    akis
    0.07
    ASCADE
    0.07
    aucoup
    0.07
    _mB
    0.07
    _mE
    0.07
    Activations Density 0.023%

    No Known Activations