© 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. 6-LLAMASCOPE-RES-32K
    11. 11930
    Prev
    Next
    INDEX
    Explanations

    instances of temptation and related concepts regarding succumbing or resisting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eel
    -0.16
    afort
    -0.15
    anela
    -0.15
    vise
    -0.15
    tec
    -0.15
    /npm
    -0.14
    erif
    -0.14
    太éĥİ
    -0.14
    YO
    -0.14
    ffe
    -0.14
    POSITIVE LOGITS
     tempted
    0.20
     tempting
    0.17
    سÙĬØ©
    0.17
     temptation
    0.17
     Tem
    0.17
     tempt
    0.17
     succ
    0.16
    achers
    0.15
    tempt
    0.15
     Byl
    0.15
    Activations Density 0.177%

    No Known Activations