© 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. 9-LLAMASCOPE-RES-32K
    11. 23369
    Prev
    Next
    INDEX
    Explanations

    references to organizations and their associative groupings

    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
    leck
    -0.17
    yx
    -0.15
     Died
    -0.15
     Nachricht
    -0.15
    ĢìĿ´
    -0.13
    vala
    -0.13
    igue
    -0.13
    ä»ĭ
    -0.13
    ¼åIJĪ
    -0.13
     def
    -0.13
    POSITIVE LOGITS
    Targets
    0.15
    TextBoxColumn
    0.15
    etcode
    0.14
    MESS
    0.14
    idlo
    0.14
    _ABI
    0.14
    avou
    0.13
    etail
    0.13
    wart
    0.13
    roc
    0.13
    Activations Density 0.237%

    No Known Activations