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. 22-LLAMASCOPE-RES-32K
    6. 11284
    Prev
    Next
    INDEX
    Explanations

    the frequent use of the word "just."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exactly
    -0.18
     only
    -0.16
    idget
    -0.16
     právÄĽ
    -0.15
    orsi
    -0.15
     именно
    -0.14
     such
    -0.14
     ONLY
    -0.14
     no
    -0.14
    rete
    -0.14
    POSITIVE LOGITS
    ifiable
    0.18
    ifying
    0.18
    uxtap
    0.17
    iban
    0.15
    ä¿Ĥ
    0.15
    born
    0.15
    _called
    0.15
    ifications
    0.15
    æģĴ
    0.14
    ified
    0.14
    Activations Density 0.091%

    No Known Activations