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. 20-LLAMASCOPE-RES-32K
    6. 21474
    Prev
    Next
    INDEX
    Explanations

    key aspects of governance and policy-making related to healthcare and societal issues

    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
    ŀĭ
    -0.15
    chner
    -0.14
    ropolis
    -0.13
    ολ
    -0.13
    cab
    -0.12
    ียว
    -0.12
    bins
    -0.12
     Brill
    -0.12
     superv
    -0.12
    eton
    -0.12
    POSITIVE LOGITS
     continue
    1.08
     continued
    1.02
     continues
    1.02
    continue
    0.96
     continuing
    0.95
     continuation
    0.89
    continued
    0.88
    ç»§ç»Ń
    0.88
    	continue
    0.85
     continu
    0.81
    Activations Density 0.521%

    No Known Activations