© 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. 30-LLAMASCOPE-RES-32K
    11. 27110
    Prev
    Next
    INDEX
    Explanations

    expressions of skepticism or criticism towards ideas and claims

    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
     Gale
    -0.17
    åĦĢ
    -0.14
    549
    -0.14
     FactoryGirl
    -0.14
    inx
    -0.14
    QT
    -0.13
    efon
    -0.13
     Seks
    -0.13
    otron
    -0.13
    à¥įà¤Ĺत
    -0.13
    POSITIVE LOGITS
     BS
    0.48
     garbage
    0.44
     bs
    0.43
     bull
    0.42
     rubbish
    0.42
     Bull
    0.41
     bulls
    0.40
     bal
    0.39
     crap
    0.38
    BS
    0.38
    Activations Density 0.271%

    No Known Activations