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. 29-LLAMASCOPE-RES-32K
    6. 12480
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs and libraries in code

    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
    OLS
    -0.14
    ing
    -0.14
    opoulos
    -0.14
    rait
    -0.14
    ogne
    -0.14
    ickers
    -0.14
    åŃĶ
    -0.13
    ftware
    -0.13
    itel
    -0.13
    rouch
    -0.13
    POSITIVE LOGITS
    .util
    0.19
    .Util
    0.18
    .utils
    0.18
    /util
    0.18
    Util
    0.17
    -util
    0.17
    util
    0.16
    -core
    0.15
    SDK
    0.15
    Core
    0.15
    Activations Density 0.171%

    No Known Activations