© 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. 2-LLAMASCOPE-RES-32K
    11. 26070
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Lo" in various contexts, likely representing a specific coding or cataloging term

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uela
    -0.17
    fono
    -0.15
    beiter
    -0.15
    ingle
    -0.15
    upt
    -0.14
    roids
    -0.14
    rema
    -0.14
    amet
    -0.14
    uju
    -0.14
    Tooltip
    -0.14
    POSITIVE LOGITS
    wner
    0.15
    çłģ
    0.14
    ycop
    0.14
    inati
    0.14
    bs
    0.14
     Bust
    0.14
    ir
    0.14
    ithe
    0.14
    ated
    0.13
    mapper
    0.13
    Activations Density 0.013%

    No Known Activations