© 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 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. 30-LLAMASCOPE-RES-32K
    11. 26214
    Prev
    Next
    INDEX
    Explanations

    various forms and variations of the word "grotesque" along with related linguistic patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Q
    -0.29
    /Q
    -0.26
    (Q
    -0.25
    ,Q
    -0.24
    <Q
    -0.22
    .Q
    -0.17
    stad
    -0.17
    _Q
    -0.17
    esar
    -0.17
    дал
    -0.17
    POSITIVE LOGITS
    qu
    0.56
    que
    0.54
    ques
    0.45
    qué
    0.39
    q
    0.38
    qui
    0.37
    QUE
    0.35
    quee
    0.35
    quer
    0.34
    queue
    0.33
    Activations Density 0.061%

    No Known Activations