© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 27-LLAMASCOPE-RES-32K
    11. 5970
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to data structures and programming concepts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     addCriterion
    -0.19
    @dynamic
    -0.14
     )↵↵↵↵↵↵↵↵
    -0.13
    .Guna
    -0.12
     VERBOSE
    -0.12
     pohod
    -0.12
     destinationViewController
    -0.11
     ÄijÃłi
    -0.11
    .Undef
    -0.11
    "class
    -0.11
    POSITIVE LOGITS
    Âłin
    0.22
    Âłs
    0.16
    Âł
    0.14
    Âłd
    0.13
     internally
    0.12
    Âłh
    0.12
    Âłn
    0.12
    Âłt
    0.12
    ERRU
    0.12
    Âłv
    0.12
    Activations Density 5.491%

    No Known Activations