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. 18-LLAMASCOPE-RES-32K
    6. 2491
    Prev
    Next
    INDEX
    Explanations

    phrases related to boasting or showcasing achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    halb
    -0.15
    ussen
    -0.15
    ¾
    -0.15
    trap
    -0.14
    ukt
    -0.14
    vez
    -0.14
    ugg
    -0.14
    wil
    -0.14
    279
    -0.13
     ún
    -0.13
    POSITIVE LOGITS
    -about
    0.18
     about
    0.18
     About
    0.16
    _about
    0.15
     having
    0.15
    ably
    0.15
    .safe
    0.15
    ãĥªãĥ¼
    0.15
    About
    0.14
    antly
    0.14
    Activations Density 0.014%

    No Known Activations