© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 16-LLAMASCOPE-RES-32K
    11. 7057
    Prev
    Next
    INDEX
    Explanations

    actions related to copying and cloning data or objects

    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
    trand
    -0.15
    quit
    -0.15
    rende
    -0.14
     batching
    -0.14
     prematurely
    -0.14
    gren
    -0.14
    æ¸
    -0.14
    exels
    -0.13
    occus
    -0.13
    terminated
    -0.13
    POSITIVE LOGITS
     copy
    0.42
     copies
    0.39
    copy
    0.38
     Copy
    0.38
    .copy
    0.37
     clone
    0.37
    .deepcopy
    0.35
     copied
    0.34
    -copy
    0.34
    .clone
    0.34
    Activations Density 0.218%

    No Known Activations