© 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. 31-LLAMASCOPE-RES-32K
    11. 30819
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to programming and networking

    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
    ój
    -0.13
    ãĤ¤ãĥĦ
    -0.13
    adil
    -0.13
    errupt
    -0.13
    ابÛĮ
    -0.12
    anut
    -0.12
    ÛĮÙĨÚ©
    -0.12
    ãĥ¼ãĥĸãĥ«
    -0.12
    Deque
    -0.12
    инов
    -0.12
    POSITIVE LOGITS
     Dom
    1.26
     dom
    1.22
    dom
    1.14
    Dom
    1.14
    -dom
    1.13
     DOM
    1.10
    DOM
    1.02
    _dom
    1.02
     Dominic
    0.99
    .dom
    0.97
    Activations Density 0.147%

    No Known Activations