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. 15-LLAMASCOPE-RES-32K
    6. 2021
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a desire for knowledge or seeking information

    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
    озв
    -0.16
     æ¨
    -0.15
    avec
    -0.15
    strand
    -0.14
    (æĹ¥
    -0.14
    upert
    -0.14
    adar
    -0.14
    onde
    -0.14
    ieg
    -0.14
    intl
    -0.14
    POSITIVE LOGITS
    GetType
    0.15
    ellig
    0.15
    564
    0.14
    DIRECT
    0.14
    Bid
    0.14
    çļĦè¯Ŀ
    0.14
     learn
    0.14
    752
    0.13
    omba
    0.13
     ÅĻÃŃj
    0.13
    Activations Density 0.052%

    No Known Activations