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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 55667
    Prev
    Next
    INDEX
    Explanations

    technical terms and identifiers commonly used in programming contexts

    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
    aises
    -0.06
    anter
    -0.06
    nen
    -0.06
    emap
    -0.06
    ouch
    -0.06
    jo
    -0.05
    Äģ
    -0.05
    oon
    -0.05
     apparent
    -0.05
     
    -0.05
    POSITIVE LOGITS
    ¡
    0.12
     ÑĤипа
    0.10
    type
    0.10
     types
    0.10
     type
    0.10
    _type
    0.10
    ç±»åŀĭ
    0.10
    -type
    0.09
    types
    0.09
     jenis
    0.09
    Activations Density 0.017%

    No Known Activations