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. 5-LLAMASCOPE-RES-32K
    6. 18493
    Prev
    Next
    INDEX
    Explanations

    phrases or references pertaining to beer brewing and its cultural significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apat
    -0.17
     itemprop
    -0.15
    wards
    -0.15
    apis
    -0.14
    veau
    -0.14
    lec
    -0.14
    allee
    -0.14
    ittel
    -0.14
    447
    -0.14
    undy
    -0.14
    POSITIVE LOGITS
    opr
    0.17
    ù
    0.14
    lage
    0.14
    lucent
    0.14
    opo
    0.14
     Bek
    0.14
    wen
    0.14
     Duy
    0.14
    mium
    0.13
    HING
    0.13
    Activations Density 0.565%

    No Known Activations