© 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. 26734
    Prev
    Next
    INDEX
    Explanations

    statements related to defendants’ arguments and legal justifications

    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
    idot
    -0.17
    LEC
    -0.17
    bourg
    -0.17
    JC
    -0.16
     REP
    -0.15
    yth
    -0.15
    .mb
    -0.15
    εξ
    -0.14
    ephy
    -0.14
    endas
    -0.14
    POSITIVE LOGITS
    olumbia
    0.16
    äre
    0.14
     Laure
    0.14
    æ´ĭ
    0.14
    antic
    0.14
    -tools
    0.13
    onte
    0.13
    ابÙĦ
    0.13
    reste
    0.13
    tik
    0.13
    Activations Density 0.613%

    No Known Activations