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. 19-LLAMASCOPE-RES-32K
    6. 6545
    Prev
    Next
    INDEX
    Explanations

    phrases that describe authenticity and natural beauty versus artificiality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ught
    -0.15
    olest
    -0.15
     án
    -0.14
     Fried
    -0.14
    anza
    -0.14
    ABB
    -0.13
     кÑĥлÑĮ
    -0.13
    arrass
    -0.13
     separ
    -0.13
    agues
    -0.13
    POSITIVE LOGITS
     real
    0.39
    real
    0.36
     natural
    0.34
    -real
    0.33
     reality
    0.32
     realism
    0.31
     Real
    0.31
    natural
    0.31
     REAL
    0.30
    _real
    0.29
    Activations Density 0.016%

    No Known Activations