© 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. 4-LLAMASCOPE-RES-32K
    11. 2825
    Prev
    Next
    INDEX
    Explanations

    data related to movies and entertainment reviews

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arters
    -0.17
    žÃŃ
    -0.16
    ault
    -0.15
    935
    -0.14
    ATRIX
    -0.14
    581
    -0.14
    ẩu
    -0.14
     Halk
    -0.14
    sÃŃ
    -0.13
    ربÙĩ
    -0.13
    POSITIVE LOGITS
     par
    0.13
    441
    0.13
    unny
    0.13
     CIF
    0.13
    /antlr
    0.13
    ãĥ¼ãĥī
    0.13
     To
    0.13
    (\'
    0.12
     puis
    0.12
     Mandarin
    0.12
    Activations Density 0.116%

    No Known Activations