© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 27-LLAMASCOPE-RES-32K
    11. 10814
    Prev
    Next
    INDEX
    Explanations

    references to community organizations and their needs for volunteers

    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
    /Dk
    -0.14
    окол
    -0.12
    ubo
    -0.11
    ritable
    -0.11
    iesta
    -0.11
    legen
    -0.11
    коз
    -0.11
    witter
    -0.11
     Äijá»Ļng
    -0.11
     Programm
    -0.10
    POSITIVE LOGITS
     use
    1.03
     uses
    0.86
     Use
    0.85
    使çĶ¨
    0.82
    Use
    0.82
     using
    0.78
     usage
    0.77
    -use
    0.77
    use
    0.77
     gebruik
    0.76
    Activations Density 1.653%

    No Known Activations