© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-32K
    6. 9735
    Prev
    Next
    INDEX
    Explanations

    instances of the word "show" and its variations, indicating a focus on demonstration or presentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    İ
    -0.15
    pch
    -0.14
    ucken
    -0.14
    landır
    -0.14
    ilogy
    -0.13
    essel
    -0.13
    leared
    -0.13
    nish
    -0.13
    arih
    -0.13
    ará
    -0.13
    POSITIVE LOGITS
     signs
    0.35
     how
    0.34
     off
    0.32
    -off
    0.29
    boat
    0.28
     up
    0.28
     why
    0.28
     Signs
    0.27
    off
    0.26
    -case
    0.26
    Activations Density 0.095%

    No Known Activations