© 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. 18-LLAMASCOPE-RES-32K
    11. 2180
    Prev
    Next
    INDEX
    Explanations

    any references to numerical values or timeframes related to events or experiences

    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
    ion
    -0.17
     же
    -0.15
    à¸łà¸²à¸Ħ
    -0.15
    kir
    -0.15
    ION
    -0.15
    gles
    -0.15
     Kir
    -0.14
    説
    -0.14
    à¤Ĥà¤ľ
    -0.14
    ÅĻÃŃm
    -0.14
    POSITIVE LOGITS
     times
    0.20
     TIMES
    0.17
     Times
    0.17
     miles
    0.15
    908
    0.15
     veces
    0.15
     mile
    0.14
    ologically
    0.14
    ially
    0.14
    ynchronously
    0.14
    Activations Density 0.116%

    No Known Activations