© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 29-LLAMASCOPE-RES-32K
    11. 14126
    Prev
    Next
    INDEX
    Explanations

    elements related to physics properties in game development or programming contexts

    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
     trú
    -0.15
    boot
    -0.15
     Carol
    -0.14
    å²Ĺ
    -0.14
    åľį
    -0.14
    azzo
    -0.14
    rightness
    -0.14
    _fault
    -0.14
     beats
    -0.13
    HEME
    -0.13
    POSITIVE LOGITS
     contact
    0.27
     Body
    0.26
     bodies
    0.26
     Contact
    0.25
    Contact
    0.25
     Bodies
    0.25
    contact
    0.25
     contacts
    0.24
    Body
    0.24
     body
    0.23
    Activations Density 0.010%

    No Known Activations