© 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. 19-LLAMASCOPE-RES-32K
    6. 1936
    Prev
    Next
    INDEX
    Explanations

    references to community organizations and advocacy groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cuban
    -0.15
    upa
    -0.15
    ape
    -0.15
     Nicar
    -0.15
     ı
    -0.14
    ALSE
    -0.14
     Nep
    -0.14
     Serbian
    -0.13
     Slovak
    -0.13
    ome
    -0.13
    POSITIVE LOGITS
     UK
    0.24
    UK
    0.20
     USA
    0.20
    à¸Ľà¸£à¸°à¸Īำ
    0.18
     Canada
    0.18
    usa
    0.17
     Australia
    0.16
     Uk
    0.15
     ÄĮR
    0.15
     Greater
    0.15
    Activations Density 0.241%

    No Known Activations