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. 30-LLAMASCOPE-RES-32K
    6. 23350
    Prev
    Next
    INDEX
    Explanations

    terms related to plant species and their properties

    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
    ighted
    -0.16
    oled
    -0.14
    à¸ł
    -0.14
    inston
    -0.14
    صر
    -0.14
    olik
    -0.14
    APPER
    -0.14
     numar
    -0.14
    ropp
    -0.14
    ẩm
    -0.14
    POSITIVE LOGITS
     purs
    0.21
     bladder
    0.20
     dock
    0.20
     Dock
    0.20
     False
    0.20
     false
    0.20
     docks
    0.19
     Api
    0.19
    celand
    0.19
     Polygon
    0.18
    Activations Density 0.071%

    No Known Activations