© 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. 9-LLAMASCOPE-RES-32K
    11. 26694
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to court decisions and remedies

    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
    èĮĤ
    -0.16
    enco
    -0.16
    lew
    -0.15
    hiba
    -0.15
    ibus
    -0.15
    lash
    -0.15
     ÑĥÑģл
    -0.15
    лÑĥÑĪ
    -0.14
    stras
    -0.14
    ëį
    -0.14
    POSITIVE LOGITS
     pilot
    0.16
     Duty
    0.16
    åĬĽçļĦ
    0.15
     duty
    0.15
    Tp
    0.15
    inan
    0.15
     DevExpress
    0.14
    à¹Ģà¸Ħ
    0.14
     case
    0.14
     èĩªåĬ¨çĶŁæĪIJ
    0.14
    Activations Density 0.129%

    No Known Activations