Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 25-LLAMASCOPE-RES-32K
    6. 18030
    Prev
    Next
    INDEX
    Explanations

    expressions and phrases indicating measurement or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĮĢ
    -0.15
    ÑĸÑĤÑĮ
    -0.14
    ırak
    -0.14
    428
    -0.14
    ichage
    -0.14
    bower
    -0.14
    bing
    -0.14
    大ä¼ļ
    -0.13
    vang
    -0.13
     Penny
    -0.13
    POSITIVE LOGITS
     piece
    1.02
     pieces
    0.91
     Piece
    0.85
    piece
    0.81
    -piece
    0.79
     Pieces
    0.79
    Piece
    0.73
    pieces
    0.73
    _piece
    0.67
    Pieces
    0.65
    Activations Density 0.155%

    No Known Activations