© 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. 26-LLAMASCOPE-RES-32K
    6. 10414
    Prev
    Next
    INDEX
    Explanations

    expressions of doubt or uncertainty regarding perseverance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xCD
    -0.15
    bette
    -0.14
    اÙĪÙĦ
    -0.14
    ếp
    -0.14
    tae
    -0.14
     reopening
    -0.14
    epam
    -0.14
     reopened
    -0.14
    /assets
    -0.14
    -assets
    -0.14
    POSITIVE LOGITS
     quit
    0.35
     give
    0.34
     giving
    0.33
     Give
    0.31
     gives
    0.30
     gave
    0.30
    Give
    0.29
     Giving
    0.29
     quits
    0.29
    give
    0.28
    Activations Density 0.185%

    No Known Activations