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. 23-LLAMASCOPE-RES-32K
    6. 658
    Prev
    Next
    INDEX
    Explanations

    elements related to HTML structure and server-side programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cher
    -0.15
    aaS
    -0.15
    cloud
    -0.14
    534
    -0.14
     Library
    -0.14
    akis
    -0.14
     wi
    -0.14
    enes
    -0.14
    finder
    -0.14
    asonry
    -0.14
    POSITIVE LOGITS
     Hyp
    0.21
     Nets
    0.20
     hyp
    0.18
     Casc
    0.18
     doGet
    0.17
    /loose
    0.17
     HTML
    0.17
    /xhtml
    0.16
     Web
    0.16
     Hyper
    0.16
    Activations Density 0.019%

    No Known Activations