© 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. 15-LLAMASCOPE-RES-32K
    11. 2831
    Prev
    Next
    INDEX
    Explanations

    words and phrases that express vulgarity or frustration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elle
    -0.20
    dl
    -0.19
    elas
    -0.17
    elli
    -0.17
    el
    -0.17
    ements
    -0.16
    ellers
    -0.16
    ess
    -0.16
    lite
    -0.16
    eler
    -0.16
    POSITIVE LOGITS
    sterol
    0.19
    ucid
    0.17
    prit
    0.17
    heck
    0.16
    iferay
    0.16
    inese
    0.16
    unteer
    0.16
    abyrin
    0.16
    itude
    0.15
    mazon
    0.15
    Activations Density 0.060%

    No Known Activations