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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 19960
    Prev
    Next
    INDEX
    Explanations

    relationships and changes in various contexts such as economics, causes, and actions

    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
    è
    -0.17
    Å¡k
    -0.16
    ÙĪÙĨÛĮ
    -0.15
    gency
    -0.15
     Disclosure
    -0.15
    ÛĮØ´ÙĨ
    -0.14
    onya
    -0.14
    Embed
    -0.14
    ivial
    -0.13
    park
    -0.13
    POSITIVE LOGITS
     input
    0.17
    .INPUT
    0.15
    олаг
    0.15
    .fa
    0.15
    input
    0.14
    .input
    0.14
    (input
    0.14
     Pamela
    0.14
     cloth
    0.14
    ibri
    0.14
    Activations Density 0.211%

    No Known Activations