© 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. 25-LLAMASCOPE-RES-32K
    11. 19626
    Prev
    Next
    INDEX
    Explanations

    mentions of institutions, authorities, and individuals involved in decision-making processes or governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    алÑĥ
    -0.15
     رÙĩ
    -0.14
    å¿Ĺ
    -0.14
    à¹Ģสร
    -0.14
    iling
    -0.14
    аÑĤов
    -0.13
    otlin
    -0.13
     residing
    -0.13
     Literary
    -0.13
    ÑĢÑĥÑĩ
    -0.13
    POSITIVE LOGITS
     responsible
    0.46
     involved
    0.46
     responsable
    0.33
     handling
    0.31
     charged
    0.30
     Responsible
    0.29
    ponsible
    0.28
    è´Łè´£
    0.27
     respons
    0.26
     working
    0.26
    Activations Density 0.361%

    No Known Activations