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. 30-LLAMASCOPE-RES-32K
    6. 11138
    Prev
    Next
    INDEX
    Explanations

    references to local governance and community initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mandal
    -0.17
     NSW
    -0.16
    Dallas
    -0.15
    uku
    -0.15
    .bn
    -0.15
    ugu
    -0.15
     ngx
    -0.14
     Newcastle
    -0.14
    öt
    -0.14
     Ashe
    -0.14
    POSITIVE LOGITS
     Michigan
    0.85
    Michigan
    0.73
     Detroit
    0.60
     Mich
    0.57
     mich
    0.57
     Lansing
    0.56
    Detroit
    0.52
     MI
    0.48
     Wolverine
    0.48
    Mich
    0.46
    Activations Density 0.182%

    No Known Activations