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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 26-LLAMASCOPE-RES-32K
    6. 1535
    Prev
    Next
    INDEX
    Explanations

    references to judicial decisions and legal principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /compiler
    -0.16
    ROP
    -0.15
    ripper
    -0.15
    커
    -0.15
    obel
    -0.14
    Mahon
    -0.14
    apr
    -0.14
    enal
    -0.14
    <quote
    -0.13
    ainment
    -0.13
    POSITIVE LOGITS
     Crown
    0.26
     crown
    0.21
     Charter
    0.17
    ENDOR
    0.15
     LAT
    0.15
    clearfix
    0.15
     Kons
    0.15
    Ĭ¶
    0.14
     ³³ ³³ ³³ ³³
    0.14
    æ³ķ
    0.14
    Activations Density 0.034%

    No Known Activations