© 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. 125459
    Prev
    Next
    INDEX
    Explanations

    specific details about locations and boundaries within a geographical 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
    izia
    -0.08
    åĪ¥
    -0.08
    _TestCase
    -0.07
    arness
    -0.07
    åŃĿ
    -0.07
    amework
    -0.07
    reh
    -0.07
    ifix
    -0.07
    دÙī
    -0.06
    ologi
    -0.06
    POSITIVE LOGITS
     center
    0.06
     centroid
    0.06
    orge
    0.06
     Hlav
    0.06
     craw
    0.05
    sti
    0.05
     centre
    0.05
    498
    0.05
    _FIN
    0.05
     actual
    0.05
    Activations Density 0.002%

    No Known Activations