© 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. 4-LLAMASCOPE-RES-32K
    11. 2649
    Prev
    Next
    INDEX
    Explanations

    references to dietary habits and health-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    weep
    -0.17
    410
    -0.16
    ider
    -0.16
    wij
    -0.15
    418
    -0.15
    reamble
    -0.14
    ailer
    -0.14
    457
    -0.14
    780
    -0.14
    vel
    -0.14
    POSITIVE LOGITS
    ãĥ¼ãĥ³
    0.16
    /loader
    0.14
    setItem
    0.14
    ãĥ«ãĤ¯
    0.14
    ÎķΤ
    0.14
    lg
    0.14
     Tight
    0.14
    .Amount
    0.13
    ãģıãģª
    0.13
    æ¯
    0.13
    Activations Density 0.381%

    No Known Activations