© 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. 13-LLAMASCOPE-RES-32K
    6. 13969
    Prev
    Next
    INDEX
    Explanations

    references to Italian culture and heritage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    纪
    -0.16
    ;set
    -0.15
    ãĥ³ãĥĩ
    -0.15
    razier
    -0.15
    antha
    -0.15
    /*č↵
    -0.14
    .Foundation
    -0.14
    楽ãģĹ
    -0.14
    ainen
    -0.14
    à¤Ĥडल
    -0.14
    POSITIVE LOGITS
     Italian
    0.20
    itÃł
    0.20
     Italy
    0.19
     Giuliani
    0.18
    Italian
    0.17
     Gi
    0.17
     Lomb
    0.17
     Rom
    0.16
    azz
    0.16
     Luca
    0.16
    Activations Density 0.463%

    No Known Activations