© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 10-LLAMASCOPE-RES-32K
    11. 9021
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically semicolons and parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atcher
    -0.16
    ique
    -0.16
    olumn
    -0.14
    ãĤ©
    -0.14
    ái
    -0.14
    gger
    -0.14
    dens
    -0.14
    sell
    -0.14
    urations
    -0.14
    leta
    -0.14
    POSITIVE LOGITS
    /*č↵
    0.16
    kel
    0.16
     âĹĦ
    0.15
    ERO
    0.15
    .PropTypes
    0.15
    inde
    0.15
    ered
    0.14
    _FOREACH
    0.14
    eron
    0.14
     toán
    0.14
    Activations Density 0.154%

    No Known Activations