© 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. 20-LLAMASCOPE-RES-32K
    11. 21143
    Prev
    Next
    INDEX
    Explanations

    promotional phrases related to downloading demos and encouraging customer engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phin
    -0.14
    ÑĢап
    -0.14
    ritz
    -0.14
    tvrt
    -0.13
     addslashes
    -0.13
    .proc
    -0.13
    ieux
    -0.13
    à¹Ģร
    -0.13
     contrib
    -0.13
    Ïģη
    -0.12
    POSITIVE LOGITS
     demo
    0.49
     sample
    0.49
     test
    0.46
     samples
    0.45
    demo
    0.44
     demonstration
    0.43
     trial
    0.42
    -sample
    0.42
    Demo
    0.42
     Sample
    0.41
    Activations Density 0.313%

    No Known Activations