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. 28-LLAMASCOPE-RES-32K
    6. 29913
    Prev
    Next
    INDEX
    Explanations

    references to web development elements and programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ossier
    -0.15
    iras
    -0.14
    Binder
    -0.14
    稿
    -0.14
    _blueprint
    -0.14
    ä¸ĭ载次æķ°
    -0.13
    μεν
    -0.13
    견
    -0.13
    addon
    -0.12
    olta
    -0.12
    POSITIVE LOGITS
     bar
    1.53
     Bar
    1.45
    bar
    1.42
    Bar
    1.39
    -bar
    1.34
    _bar
    1.25
     BAR
    1.23
    -Bar
    1.22
    BAR
    1.19
    .bar
    1.18
    Activations Density 0.384%

    No Known Activations