© 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. 21-LLAMASCOPE-RES-32K
    11. 5134
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "in (adjective) detail" or variations emphasizing the depth of description

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ubl
    -0.16
    oug
    -0.15
    usch
    -0.15
    itta
    -0.14
     Kund
    -0.14
    ridge
    -0.14
    sted
    -0.14
    ı
    -0.14
    ä»Ģ
    -0.14
     Schmidt
    -0.14
    POSITIVE LOGITS
     detail
    0.52
    detail
    0.43
     Detail
    0.40
    -detail
    0.34
    Detail
    0.34
     detal
    0.33
    _detail
    0.32
    .detail
    0.32
     detalle
    0.31
     details
    0.30
    Activations Density 0.085%

    No Known Activations