Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 30-LLAMASCOPE-RES-32K
    6. 24364
    Prev
    Next
    INDEX
    Explanations

    positive attributes and concepts associated with spirituality and love

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æľį
    -0.14
    ToLeft
    -0.14
    <*
    -0.14
    ÑĢÑĥÑģ
    -0.13
    odos
    -0.13
    775
    -0.13
    iral
    -0.13
    phet
    -0.13
    Ùĥرة
    -0.13
     localization
    -0.13
    POSITIVE LOGITS
     peace
    0.37
     strength
    0.31
     Peace
    0.31
     hope
    0.30
     light
    0.29
     joy
    0.28
    peace
    0.27
     Joy
    0.27
     beauty
    0.27
     JO
    0.27
    Activations Density 0.556%

    No Known Activations