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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 18-LLAMASCOPE-RES-32K
    11. 10173
    Prev
    Next
    INDEX
    Explanations

    instances of issues or problems encountered while using software or code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hopefully
    -0.14
    awk
    -0.14
    decess
    -0.14
    å·
    -0.14
    istine
    -0.14
    ige
    -0.14
    irez
    -0.14
    اسÛĮ
    -0.13
    еÑĢк
    -0.13
    Ø´ÙĪ
    -0.13
    POSITIVE LOGITS
     when
    0.21
     When
    0.17
    when
    0.17
    _HOT
    0.16
     none
    0.16
    ноÑĪ
    0.16
     Wah
    0.15
    ãĥ¶
    0.15
     aku
    0.15
    ÏħÏĦÏĮ
    0.15
    Activations Density 0.094%

    No Known Activations