© 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. 26-LLAMASCOPE-RES-32K
    11. 9750
    Prev
    Next
    INDEX
    Explanations

    references to locations and structures within a larger context

    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
    -has
    -0.17
     ÙĨدارد
    -0.16
    ä¸įä¼ļ
    -0.15
    (has
    -0.15
     nemá
    -0.14
    yster
    -0.13
     hätte
    -0.13
     nemÄĽl
    -0.13
    é½
    -0.13
     origin
    -0.13
    POSITIVE LOGITS
     lies
    0.45
     lie
    0.41
     there
    0.34
     are
    0.34
     stands
    0.31
     stood
    0.31
     sits
    0.31
     stand
    0.29
     exists
    0.28
    lie
    0.28
    Activations Density 0.264%

    No Known Activations