© 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. 15-LLAMASCOPE-RES-32K
    11. 2331
    Prev
    Next
    INDEX
    Explanations

    indicators of authorship and citation in written content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    plier
    -0.16
     Fibonacci
    -0.14
    elper
    -0.14
    lessly
    -0.13
    SPATH
    -0.13
     Hyp
    -0.13
    สะ
    -0.13
    elts
    -0.13
    elong
    -0.13
    preter
    -0.13
    POSITIVE LOGITS
     Uncategorized
    0.17
     DISCLAIM
    0.16
     jadx
    0.14
    utenberg
    0.14
    ılı
    0.13
    (Arg
    0.13
    ë¡Ģ
    0.13
    abcdefghijkl
    0.13
    ôn
    0.13
     strtoupper
    0.13
    Activations Density 0.042%

    No Known Activations