© 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. 27-LLAMASCOPE-RES-32K
    11. 12832
    Prev
    Next
    INDEX
    Explanations

    words associated with deceptive or misleading behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lal
    -0.18
     Loren
    -0.16
     Lilly
    -0.16
    æ½
    -0.15
    onden
    -0.15
    ÄŁine
    -0.14
     Liquid
    -0.14
     Lair
    -0.14
    нев
    -0.14
     Lowe
    -0.14
    POSITIVE LOGITS
    les
    0.56
    led
    0.52
    ling
    0.45
    LES
    0.44
    ler
    0.43
    lers
    0.38
    lesh
    0.38
    ledo
    0.33
    le
    0.31
    LED
    0.30
    Activations Density 0.069%

    No Known Activations