© 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. 5418
    Prev
    Next
    INDEX
    Explanations

    phrases indicating misfortune or luck in circumstances

    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
     Tob
    -0.14
    лиÑĨ
    -0.14
    490
    -0.14
    rai
    -0.14
    uchi
    -0.14
    alach
    -0.13
    ALES
    -0.13
     railing
    -0.13
     whenever
    -0.13
    lang
    -0.13
    POSITIVE LOGITS
     bother
    0.23
     courage
    0.20
     enough
    0.18
     tem
    0.18
     Tem
    0.18
     fores
    0.17
     courtesy
    0.17
    iyat
    0.16
     trouble
    0.16
    ÅĽnie
    0.16
    Activations Density 0.115%

    No Known Activations