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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 29-LLAMASCOPE-RES-32K
    11. 21174
    Prev
    Next
    INDEX
    Explanations

    words indicating actions or instructions

    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
    —an
    -0.22
    æĺ¯ä¸Ģ个
    -0.20
    ä¸ĢåĢĭ
    -0.19
     einer
    -0.17
    ä¸Ģç§į
    -0.16
     sebuah
    -0.16
    someone
    -0.16
    æĺ¯ä¸Ģ
    -0.15
     an
    -0.15
     someone
    -0.15
    POSITIVE LOGITS
    a
    0.21
     a
    0.18
     ago
    0.17
    is
    0.15
    aghan
    0.15
     Perr
    0.14
     gang
    0.13
    ages
    0.13
    anken
    0.13
    ’a
    0.13
    Activations Density 0.113%

    No Known Activations