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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-32K
    11. 26365
    Prev
    Next
    INDEX
    Explanations

    concepts related to pricing and trading in environmental policy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esel
    -0.17
    ibble
    -0.17
    xdf
    -0.15
    iros
    -0.15
     Dent
    -0.14
     dint
    -0.14
    asted
    -0.14
    iped
    -0.14
    amps
    -0.14
    ers
    -0.14
    POSITIVE LOGITS
     ÑģоÑĢ
    0.15
     Goodman
    0.14
     BASIS
    0.14
     reform
    0.14
     wParam
    0.14
    TEE
    0.14
    urovision
    0.14
    etur
    0.14
    ulumi
    0.14
    /preferences
    0.14
    Activations Density 0.076%

    No Known Activations