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. 5-LLAMASCOPE-RES-32K
    6. 319
    Prev
    Next
    INDEX
    Explanations

    references to governmental policies and their impacts on society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inh
    -0.15
    [d
    -0.14
    iday
    -0.14
    673
    -0.14
     Billboard
    -0.14
    oks
    -0.14
     Germ
    -0.13
    ocate
    -0.13
     Chapman
    -0.13
    gate
    -0.13
    POSITIVE LOGITS
    rikes
    0.17
    .openg
    0.15
    Ìģ
    0.15
    \Desktop
    0.15
    Ìĥ
    0.14
    atypes
    0.14
    ̧
    0.14
    UES
    0.14
    ngo
    0.14
     htmlentities
    0.14
    Activations Density 2.635%

    No Known Activations