© 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. 23-LLAMASCOPE-RES-32K
    11. 12312
    Prev
    Next
    INDEX
    Explanations

    variables or identifiers related to programming or code structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Å¡il
    -0.15
    /stdc
    -0.13
    acs
    -0.13
    Anything
    -0.13
    ederland
    -0.13
     brainstorm
    -0.13
    anda
    -0.13
    engo
    -0.13
    iscopal
    -0.13
    adaki
    -0.13
    POSITIVE LOGITS
    eer
    0.16
    andex
    0.13
    ricks
    0.13
    ONUS
    0.13
    masked
    0.13
    stub
    0.13
     Vend
    0.13
    tz
    0.12
    AREST
    0.12
    íĸ¥
    0.12
    Activations Density 0.071%

    No Known Activations