© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-32K
    6. 6811
    Prev
    Next
    INDEX
    Explanations

    programming constructs, particularly those related to functions and data-binding in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adla
    -0.17
    icks
    -0.16
    otty
    -0.15
    æĬ
    -0.15
    opup
    -0.15
    ãĥķãĥ¬
    -0.15
    коз
    -0.14
    eczy
    -0.14
     Aires
    -0.14
    esz
    -0.14
    POSITIVE LOGITS
     PT
    0.15
    976
    0.15
    872
    0.15
    夫人
    0.14
     personnel
    0.14
    çĽ
    0.14
    tep
    0.14
     personel
    0.14
    istani
    0.14
    il
    0.13
    Activations Density 0.094%

    No Known Activations