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. 20-LLAMASCOPE-RES-32K
    6. 23809
    Prev
    Next
    INDEX
    Explanations

    references to specific movies or popular culture events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocuk
    -0.16
    istar
    -0.15
    IXEL
    -0.15
    ixel
    -0.14
    verture
    -0.13
    tures
    -0.13
    çŁ¢
    -0.13
    ships
    -0.13
    ixa
    -0.13
    ķĮ
    -0.13
    POSITIVE LOGITS
    émon
    0.17
    lic
    0.16
    esome
    0.16
    aoke
    0.15
    ducation
    0.15
    -ing
    0.15
    tober
    0.15
    -ie
    0.14
    ly
    0.14
     squared
    0.14
    Activations Density 0.221%

    No Known Activations