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. 15-LLAMASCOPE-RES-32K
    6. 9377
    Prev
    Next
    INDEX
    Explanations

    references to authors, publications, and their respective citations in scientific research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Bloc
    -0.14
    $__
    -0.14
    ãģĿãģĹãģ¦
    -0.13
     (~(
    -0.13
    splash
    -0.13
    wdx
    -0.13
     sockfd
    -0.13
     Záp
    -0.13
    _consts
    -0.13
    patible
    -0.13
    POSITIVE LOGITS
     et
    0.18
    umerator
    0.14
     straw
    0.14
    ãĢģ
    0.14
    lsen
    0.14
    å¡ļ
    0.13
    isen
    0.13
     mak
    0.13
    ants
    0.13
    uge
    0.13
    Activations Density 0.107%

    No Known Activations