© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 30-LLAMASCOPE-RES-32K
    11. 21705
    Prev
    Next
    INDEX
    Explanations

    prominent names of authors and titles of artistic works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     .↵↵
    -0.23
    ï¼īãĢĤ↵↵
    -0.21
    .*;↵↵
    -0.21
    /.↵↵
    -0.19
     ).↵↵
    -0.19
    .↵↵
    -0.19
    ãĢĤãĢį↵↵
    -0.19
     [âĢ¦]↵↵
    -0.19
     ,↵↵
    -0.18
    ..↵↵
    -0.18
    POSITIVE LOGITS
    ↵
    0.79
    à¥Ģ↵
    0.51
    ा↵
    0.51
    à¥ĩ↵
    0.48
    à¥ĩà¤Ĥ↵
    0.48
    )↵
    0.47
    "↵
    0.45
    '↵
    0.43
    ]↵
    0.42
    ี↵
    0.42
    Activations Density 2.380%

    No Known Activations