© 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. 20-LLAMASCOPE-RES-32K
    11. 31274
    Prev
    Next
    INDEX
    Explanations

    emotional responses and challenges related to new experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Last
    -0.15
     Recently
    -0.14
    agg
    -0.14
     Next
    -0.14
    ModifiedDate
    -0.14
    imore
    -0.13
    ilan
    -0.13
     artık
    -0.13
     Third
    -0.13
    orz
    -0.13
    POSITIVE LOGITS
     initially
    1.13
     initial
    1.04
    initial
    0.97
     Initially
    0.93
    Initially
    0.87
     inicial
    0.83
     Initial
    0.82
    Initial
    0.80
    æľĢåĪĿ
    0.77
    _initial
    0.73
    Activations Density 0.982%

    No Known Activations