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. 4-LLAMASCOPE-RES-32K
    6. 14536
    Prev
    Next
    INDEX
    Explanations

    references to financial contributions and obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    illy
    -0.16
    iras
    -0.16
     cho
    -0.15
    ĸ
    -0.14
    ãĥ«ãĥķ
    -0.14
    chos
    -0.14
    asto
    -0.14
     gratuiti
    -0.14
    iers
    -0.14
    ¥¿
    -0.14
    POSITIVE LOGITS
    td
    0.17
    ugu
    0.17
    of
    0.16
    amil
    0.14
     trademarks
    0.14
    ·»
    0.14
    orman
    0.13
     Jab
    0.13
    oyo
    0.13
    èĨľ
    0.13
    Activations Density 0.388%

    No Known Activations