© 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. 31223
    Prev
    Next
    INDEX
    Explanations

    discussions about hypocrisy and moral inconsistencies in behavior and beliefs

    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
    lob
    -0.16
     Mechan
    -0.16
    enef
    -0.14
    ãĥ¼ãĥĵ
    -0.14
    wit
    -0.14
    rost
    -0.14
    toolbox
    -0.14
     mercy
    -0.14
    liž
    -0.13
    eka
    -0.13
    POSITIVE LOGITS
     behavior
    0.42
     conduct
    0.40
    è¡Į为
    0.38
     actions
    0.38
     behaviour
    0.36
     behaviors
    0.36
     Behavior
    0.35
    behavior
    0.34
    Behavior
    0.31
     повед
    0.31
    Activations Density 0.301%

    No Known Activations