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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-LLAMASCOPE-RES-32K
    6. 23483
    Prev
    Next
    INDEX
    Explanations

    numerical data or values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vyk
    -0.14
    ry
    -0.14
    eries
    -0.13
    _DECLARE
    -0.13
    elves
    -0.13
    mf
    -0.13
    UGHT
    -0.13
     zemi
    -0.13
    ertools
    -0.13
    uden
    -0.12
    POSITIVE LOGITS
    inish
    0.14
    262
    0.14
    775
    0.13
    924
    0.13
    331
    0.13
     \↵
    0.13
    ¥IJ
    0.13
    enco
    0.13
    921
    0.12
     Particle
    0.12
    Activations Density 0.878%

    No Known Activations