© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 19-LLAMASCOPE-RES-32K
    11. 1754
    Prev
    Next
    INDEX
    Explanations

    instances of cheating and unethical behavior in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ade
    -0.18
    iyan
    -0.16
    ÑĢен
    -0.14
     Kültür
    -0.14
    _compat
    -0.14
    avin
    -0.14
    landa
    -0.14
    pta
    -0.14
     رضا
    -0.14
     compat
    -0.14
    POSITIVE LOGITS
     cheating
    0.41
     cheat
    0.39
     che
    0.36
     cheats
    0.36
     Che
    0.33
    che
    0.31
     cheated
    0.31
    -che
    0.31
     Cheat
    0.30
    _che
    0.29
    Activations Density 0.215%

    No Known Activations