© 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. 16-LLAMASCOPE-RES-32K
    11. 9178
    Prev
    Next
    INDEX
    Explanations

    political titles and terms related to the U.S. Senate and its elections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulk
    -0.17
    ULK
    -0.16
    ãĥ«ãĤ¯
    -0.15
    ìļ©
    -0.14
     later
    -0.14
     Transit
    -0.14
    éķľ
    -0.14
     éķ
    -0.14
    atti
    -0.14
    uye
    -0.14
    POSITIVE LOGITS
     existing
    0.35
     Existing
    0.30
    Existing
    0.30
    existing
    0.27
    (existing
    0.25
    -existing
    0.24
     current
    0.24
    _existing
    0.23
     oldest
    0.21
     decades
    0.20
    Activations Density 0.007%

    No Known Activations