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. 27-LLAMASCOPE-RES-32K
    6. 129
    Prev
    Next
    INDEX
    Explanations

    steps and instructions related to software processes or configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odyn
    -0.17
    íķij
    -0.17
    æĹıèĩªæ²»
    -0.16
    озв
    -0.15
    stery
    -0.15
    .sav
    -0.15
    ,www
    -0.14
    ÃĹ↵↵
    -0.14
     Recap
    -0.14
    CRET
    -0.14
    POSITIVE LOGITS
     under
    0.24
     expand
    0.24
     scroll
    0.24
     locate
    0.23
     Under
    0.23
     select
    0.23
    under
    0.22
     click
    0.21
    Under
    0.21
     underneath
    0.21
    Activations Density 0.038%

    No Known Activations