© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 11-LLAMASCOPE-RES-32K
    11. 21235
    Prev
    Next
    INDEX
    Explanations

    phrases related to the creation and impact of content or projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ieu
    -0.17
    iston
    -0.16
    ĵåIJį
    -0.16
    ONO
    -0.16
    inkel
    -0.15
    umo
    -0.15
    uku
    -0.15
    ìĬ¤íħĮ
    -0.15
    GLOSS
    -0.15
    .eu
    -0.15
    POSITIVE LOGITS
     precisely
    0.15
    ç«
    0.14
    772
    0.14
     soundtrack
    0.14
    Ĥ
    0.14
    _ATTR
    0.13
    nof
    0.13
     Parliamentary
    0.13
    ribly
    0.13
    nard
    0.13
    Activations Density 0.363%

    No Known Activations