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. 23-LLAMASCOPE-RES-32K
    6. 21279
    Prev
    Next
    INDEX
    Explanations

    references to musical or cultural institutions and prominent musical figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pron
    -0.17
    pron
    -0.17
    cene
    -0.15
    AccessException
    -0.15
    λί
    -0.15
    chai
    -0.14
    ayers
    -0.14
    áv
    -0.14
    ritable
    -0.14
     ÑĤÑĢÑĥ
    -0.13
    POSITIVE LOGITS
    кÑĥп
    0.14
    åĵ
    0.14
    hed
    0.14
    æŁ»
    0.14
    uct
    0.14
     cub
    0.14
    ertas
    0.14
     umb
    0.13
    sects
    0.13
    ä¸
    0.13
    Activations Density 0.127%

    No Known Activations