© 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. 28-LLAMASCOPE-RES-32K
    11. 17968
    Prev
    Next
    INDEX
    Explanations

    references to specific amounts or measurements of burdens or problems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cứ
    -0.15
    оваÑĢи
    -0.14
    _both
    -0.13
    à¸ķลà¸Ńà¸Ķ
    -0.13
    ÎŃνÏĦ
    -0.13
     treff
    -0.13
    елÑĮзÑı
    -0.12
    uars
    -0.12
    ãģĿãĤĮãģ¯
    -0.11
    ucid
    -0.11
    POSITIVE LOGITS
     some
    1.23
    some
    1.05
     Some
    0.98
    Some
    0.92
     SOME
    0.83
    ä¸ĢäºĽ
    0.81
    .some
    0.79
    _some
    0.79
     einige
    0.75
     bazı
    0.69
    Activations Density 1.294%

    No Known Activations