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. 16-LLAMASCOPE-RES-32K
    6. 6124
    Prev
    Next
    INDEX
    Explanations

    references to musical instruments and their specific playing techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ::_
    -0.16
    .isActive
    -0.15
    atform
    -0.15
    ër
    -0.14
    ãĤ«ãĥ¼
    -0.14
    upal
    -0.14
    ãĥ¼ãĥijãĥ¼
    -0.14
    avana
    -0.13
    uste
    -0.13
    æĦı
    -0.13
    POSITIVE LOGITS
    éĩĩç͍
    0.18
    Using
    0.17
     resort
    0.17
    switch
    0.17
     using
    0.17
     Using
    0.16
     switched
    0.16
    choice
    0.16
     use
    0.16
     switch
    0.16
    Activations Density 0.150%

    No Known Activations