© 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. 17-LLAMASCOPE-RES-32K
    11. 20228
    Prev
    Next
    INDEX
    Explanations

    references to the Trojan horse concept or Trojan malware

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ares
    -0.15
    cript
    -0.15
    letal
    -0.15
    entials
    -0.14
    unda
    -0.14
    oren
    -0.14
    redients
    -0.14
     пÑĢиг
    -0.14
    éĹ
    -0.14
    urname
    -0.14
    POSITIVE LOGITS
     Tro
    0.18
     tro
    0.18
    UBLE
    0.18
    adero
    0.17
    Tro
    0.16
    oux
    0.15
     Trou
    0.15
    lox
    0.15
    ppo
    0.14
    UMB
    0.14
    Activations Density 0.020%

    No Known Activations