Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 28-LLAMASCOPE-RES-32K
    6. 23213
    Prev
    Next
    INDEX
    Explanations

    references to legal roles and the judiciary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chet
    -0.15
    ë°ĺ
    -0.14
     Fate
    -0.13
     tar
    -0.13
     regulators
    -0.13
    ember
    -0.13
     ranking
    -0.13
    UNE
    -0.13
     Tar
    -0.13
     Company
    -0.13
    POSITIVE LOGITS
     court
    0.24
     civil
    0.24
    -court
    0.23
     dock
    0.22
     cas
    0.22
    Court
    0.22
    civil
    0.21
    bench
    0.21
     cour
    0.21
    ourt
    0.21
    Activations Density 0.047%

    No Known Activations