Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 29-LLAMASCOPE-RES-32K
    6. 17879
    Prev
    Next
    INDEX
    Explanations

    closing braces and certain separators in code or structured text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ech
    -0.15
     Bowen
    -0.15
    ãĤ«ãĥĨãĤ´ãĥª
    -0.14
    rew
    -0.14
    avin
    -0.14
     bows
    -0.14
    .Observable
    -0.13
     bow
    -0.13
    .framework
    -0.13
    PWM
    -0.13
    POSITIVE LOGITS
     pub
    0.42
    pub
    0.39
     fn
    0.38
    fn
    0.33
    #[
    0.32
    	pub
    0.31
     macro
    0.30
     #[
    0.28
    .pub
    0.28
    Pub
    0.27
    Activations Density 0.001%

    No Known Activations