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. 8-LLAMASCOPE-RES-32K
    6. 1638
    Prev
    Next
    INDEX
    Explanations

    financial figures and related numerical actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cage
    -0.15
    undra
    -0.15
    ازÛĮ
    -0.14
    krom
    -0.14
    ampion
    -0.14
    _specs
    -0.14
    ãĤ¸ãĤ¢
    -0.14
    á»Ŀ
    -0.13
    .Tween
    -0.13
    footer
    -0.13
    POSITIVE LOGITS
     similarly
    0.15
    ableView
    0.15
    ispens
    0.15
    ldr
    0.15
    acos
    0.14
    apesh
    0.14
    esk
    0.13
    ayah
    0.13
    olders
    0.13
     Hind
    0.13
    Activations Density 0.658%

    No Known Activations