Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 1-LLAMASCOPE-RES-32K
    6. 4426
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "uit" (which means "out" in Dutch)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 1-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alling
    -0.16
    ients
    -0.15
    atos
    -0.15
    igned
    -0.15
    antry
    -0.15
     bif
    -0.14
    anten
    -0.14
    _executor
    -0.14
     Bulg
    -0.14
    itten
    -0.14
    POSITIVE LOGITS
    etooth
    0.21
    že
    0.16
    ritz
    0.15
    ãĥ³ãĤ¯
    0.15
    enable
    0.15
     wParam
    0.15
    ctor
    0.15
    ULATION
    0.14
    zen
    0.14
    park
    0.14
    Activations Density 0.002%

    No Known Activations