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

    Neuronpedia

    APICircuit 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. 29-LLAMASCOPE-RES-32K
    6. 3106
    Prev
    Next
    INDEX
    Explanations

    references to interconnected materials and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tiles
    -0.20
     tiles
    -0.17
    Tiles
    -0.16
    çĵ
    -0.16
     tile
    -0.16
     плиÑĤ
    -0.15
    ovie
    -0.15
    ofilm
    -0.15
    _NR
    -0.14
    askets
    -0.14
    POSITIVE LOGITS
     stick
    0.50
     sticks
    0.48
     Stick
    0.43
    Stick
    0.42
    stick
    0.42
    sticks
    0.38
     pole
    0.37
     poles
    0.36
     shaft
    0.36
     rods
    0.36
    Activations Density 0.261%

    No Known Activations