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. 29-LLAMASCOPE-RES-32K
    6. 3485
    Prev
    Next
    INDEX
    Explanations

    terms related to construction tools and equipment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dag
    -0.19
    raki
    -0.15
    кÑĢа
    -0.15
    ÑĢел
    -0.15
    PIO
    -0.15
    emma
    -0.14
    turnstile
    -0.14
    irl
    -0.14
    .IContainer
    -0.14
     tiener
    -0.14
    POSITIVE LOGITS
     Mak
    0.26
     cord
    0.25
    cord
    0.24
     Cord
    0.21
     Concrete
    0.20
     Tool
    0.20
     Dew
    0.20
     SDS
    0.20
     dew
    0.20
    Concrete
    0.20
    Activations Density 0.004%

    No Known Activations