© 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. 23300
    Prev
    Next
    INDEX
    Explanations

    phrases related to the act of extracting or obtaining information or resources

    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
    /people
    -0.16
    agn
    -0.15
     prefect
    -0.14
    amas
    -0.14
    struk
    -0.14
    elik
    -0.14
    amel
    -0.14
    im
    -0.14
    ais
    -0.14
    etary
    -0.14
    POSITIVE LOGITS
     from
    0.21
     khá»ıi
    0.19
     dara
    0.19
    à¸Īาà¸ģ
    0.17
    -from
    0.17
     dari
    0.17
    FromClass
    0.17
    ivism
    0.16
    ivist
    0.16
    ively
    0.15
    Activations Density 0.065%

    No Known Activations