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. 16-LLAMASCOPE-RES-32K
    6. 22043
    Prev
    Next
    INDEX
    Explanations

    newly released applications and their functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /cgi
    -0.18
    opy
    -0.16
     str
    -0.16
     Internet
    -0.15
    ams
    -0.14
     Mail
    -0.14
    raquo
    -0.14
     cdr
    -0.14
     Intermediate
    -0.14
    ekt
    -0.14
    POSITIVE LOGITS
     app
    0.35
    .app
    0.27
     App
    0.24
    app
    0.22
     apps
    0.22
    App
    0.21
    APP
    0.20
     APP
    0.20
    _app
    0.19
    (app
    0.18
    Activations Density 0.161%

    No Known Activations