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. 11-LLAMASCOPE-RES-32K
    6. 16527
    Prev
    Next
    INDEX
    Explanations

    references to literary figures or elements related to literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    undy
    -0.16
    ÑĮко
    -0.15
    esda
    -0.14
    ecome
    -0.14
    alez
    -0.14
    ez
    -0.13
    aic
    -0.13
    ombat
    -0.13
    оÑĩки
    -0.12
    icode
    -0.12
    POSITIVE LOGITS
    oki
    0.14
    adlo
    0.14
    kinci
    0.14
    λοι
    0.13
     nues
    0.13
    han
    0.12
    izo
    0.12
    â̦the
    0.12
    .createSequentialGroup
    0.12
    xBB
    0.12
    Activations Density 0.253%

    No Known Activations