© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 25-LLAMASCOPE-RES-32K
    11. 10552
    Prev
    Next
    INDEX
    Explanations

    function definitions and control structures within programming code

    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
    isel
    -0.18
    à¥Ĥन
    -0.15
     keer
    -0.15
    ipt
    -0.14
    uss
    -0.13
    chten
    -0.13
    >Returns
    -0.13
    etwork
    -0.13
    weg
    -0.13
    جاج
    -0.12
    POSITIVE LOGITS
    erdem
    0.14
    edBy
    0.14
    IIIK
    0.14
    tul
    0.13
    edis
    0.12
    \application
    0.12
    ibold
    0.12
    "[
    0.12
    itÃł
    0.12
    iete
    0.12
    Activations Density 0.185%

    No Known Activations