© 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. 60776
    Prev
    Next
    INDEX
    Explanations

    sets of numerical data

    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
    encia
    -0.06
     Row
    -0.06
    ilater
    -0.06
     decrement
    -0.06
    dao
    -0.06
    öt
    -0.06
     Kab
    -0.06
     row
    -0.05
    emmel
    -0.05
    Row
    -0.05
    POSITIVE LOGITS
    imdi
    0.07
    bons
    0.07
    _PHP
    0.07
    ãģĭãģªãģĦ
    0.06
    ket
    0.06
    atin
    0.06
    ìŀIJìĿ¸
    0.06
    hone
    0.06
    ATIO
    0.06
    AREN
    0.06
    Activations Density 0.000%

    No Known Activations