© 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. 29-LLAMASCOPE-RES-32K
    11. 16608
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Ok" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anca
    -0.17
    enko
    -0.16
    agnar
    -0.16
    PLY
    -0.16
    fty
    -0.16
    addy
    -0.15
    ença
    -0.15
    ials
    -0.15
    IZE
    -0.15
    encer
    -0.15
    POSITIVE LOGITS
    tober
    0.34
    lahoma
    0.30
    anagan
    0.27
    lah
    0.26
    ahoma
    0.26
    hots
    0.23
    ategor
    0.22
    amoto
    0.21
    asaki
    0.20
    ays
    0.20
    Activations Density 0.015%

    No Known Activations