© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 20-LLAMASCOPE-RES-32K
    6. 13616
    Prev
    Next
    INDEX
    Explanations

    references to helicopters and their operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ẩm
    -0.15
     Atomic
    -0.14
    .scalablytyped
    -0.14
    ода
    -0.14
     automobiles
    -0.14
     atomic
    -0.14
    íĻĢ
    -0.14
     Drivers
    -0.13
     Automobile
    -0.13
    cean
    -0.13
    POSITIVE LOGITS
     helicopter
    0.34
     helicopters
    0.34
     Hel
    0.29
     hel
    0.29
    hel
    0.27
     helicopt
    0.27
    Hel
    0.26
     rotor
    0.23
     charter
    0.22
    _HEL
    0.20
    Activations Density 0.049%

    No Known Activations