© 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. 16-LLAMASCOPE-RES-32K
    11. 8180
    Prev
    Next
    INDEX
    Explanations

    elements and structure related to programming or data handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Harrison
    -0.17
    toy
    -0.14
    etak
    -0.14
    ().
    -0.13
     ones
    -0.13
    pen
    -0.13
     Benson
    -0.13
    =DB
    -0.13
    unsch
    -0.13
    chk
    -0.13
    POSITIVE LOGITS
    IFF
    0.16
    feit
    0.15
    .TryParse
    0.15
    rvine
    0.14
    ureka
    0.14
    onom
    0.14
    ãĤ¢ãĥ¼
    0.14
    ัà¸Ļà¸ĺ
    0.13
    hud
    0.13
     Futures
    0.13
    Activations Density 0.186%

    No Known Activations