© 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. 3958
    Prev
    Next
    INDEX
    Explanations

    references to a specific person's name and variations of the word "kayak."

    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
    elig
    -0.15
     вÑĢемени
    -0.15
    noc
    -0.15
    елик
    -0.14
    à§į
    -0.14
    imple
    -0.14
    apesh
    -0.14
     Torres
    -0.14
    oretical
    -0.13
    undle
    -0.13
    POSITIVE LOGITS
    تÙĩ
    0.17
    ounty
    0.14
    yth
    0.14
    -peer
    0.14
    TI
    0.14
    ovol
    0.14
    DF
    0.14
    lients
    0.14
    uish
    0.14
    ogi
    0.14
    Activations Density 0.007%

    No Known Activations