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. 31-LLAMASCOPE-RES-32K
    6. 6075
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to data structures and types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <KeyValuePair
    -0.21
    ï¼ŁãĢį↵↵
    -0.13
    ï¼ģãĢį↵↵
    -0.12
    ï¼Ł”↵↵
    -0.11
    ï¼ģï¼ģ↵↵
    -0.10
    <HashMap
    -0.10
    Æ¡
    -0.10
    iÅŁti
    -0.10
    iverz
    -0.10
    ï¼ģ”↵↵
    -0.10
    POSITIVE LOGITS
     <
    0.83
    <
    0.69
    .<
    0.63
    ,<
    0.63
    <a
    0.61
    :<
    0.60
     </
    0.59
     (<
    0.59
    /<
    0.59
    )<
    0.58
    Activations Density 2.510%

    No Known Activations