© 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. 26-LLAMASCOPE-RES-32K
    11. 15226
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs and coding functions related to policies

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    )(__
    -0.15
     divided
    -0.15
    _TYPED
    -0.13
     ("
    -0.13
    alic
    -0.12
    ughter
    -0.12
    ospace
    -0.12
    ordum
    -0.12
     ("<
    -0.12
    +len
    -0.12
    POSITIVE LOGITS
     *
    0.55
    *
    0.41
     star
    0.40
     *=
    0.40
     aster
    0.39
    =*
    0.39
     starred
    0.38
     *↵
    0.36
     *,
    0.35
     stars
    0.35
    Activations Density 0.212%

    No Known Activations