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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 26-LLAMASCOPE-RES-32K
    6. 10623
    Prev
    Next
    INDEX
    Explanations

    words indicating positive feelings or states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onest
    -0.15
    urette
    -0.14
    las
    -0.14
     اÙĦعÙħ
    -0.14
     Wass
    -0.14
    anou
    -0.14
    ÏĦÎŃ
    -0.14
    'gc
    -0.14
    емо
    -0.14
    estroy
    -0.14
    POSITIVE LOGITS
    igu
    0.17
    æį®
    0.16
    inka
    0.15
    _BT
    0.15
     bearing
    0.15
     bear
    0.15
    EEK
    0.15
    -toast
    0.14
    icina
    0.14
    lij
    0.14
    Activations Density 0.002%

    No Known Activations