© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 26-LLAMASCOPE-RES-32K
    6. 11865
    Prev
    Next
    INDEX
    Explanations

    specific patterns and references related to bodily functions and health conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    actionDate
    -0.16
    itte
    -0.14
    ë¡Ģ
    -0.14
    微软éĽħé»ij
    -0.14
     Linden
    -0.14
     Lowe
    -0.14
    isman
    -0.14
    asis
    -0.13
     trùng
    -0.13
    lld
    -0.13
    POSITIVE LOGITS
    ular
    0.65
    ul
    0.63
    ulation
    0.60
    ula
    0.59
    ulate
    0.56
    uler
    0.54
    ulated
    0.53
    ulo
    0.53
    ulating
    0.52
    ULAR
    0.51
    Activations Density 0.068%

    No Known Activations