© 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. 20-LLAMASCOPE-RES-32K
    11. 7689
    Prev
    Next
    INDEX
    Explanations

    instances of the word "keep" or its variations emphasizing persistence or continuity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ughter
    -0.16
    orc
    -0.16
    apon
    -0.15
    illery
    -0.15
    asin
    -0.15
    hood
    -0.14
    ully
    -0.14
    atat
    -0.14
    oppins
    -0.14
    hed
    -0.14
    POSITIVE LOGITS
     pace
    0.30
     tabs
    0.30
     track
    0.27
    alive
    0.24
    _alive
    0.23
     Tabs
    0.23
    ake
    0.23
    AKE
    0.21
    pace
    0.20
    akes
    0.20
    Activations Density 0.040%

    No Known Activations