© 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. 22-LLAMASCOPE-RES-32K
    11. 16458
    Prev
    Next
    INDEX
    Explanations

    phrases related to good and bad faith in interactions and negotiations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÏģιÏĥ
    -0.15
    æļ
    -0.15
    agli
    -0.14
    opus
    -0.14
    ÙģÙĪ
    -0.14
    Ñħи
    -0.14
     jezd
    -0.13
    bower
    -0.13
    agate
    -0.13
    ls
    -0.13
    POSITIVE LOGITS
     good
    0.52
    good
    0.45
     Good
    0.44
     faith
    0.44
    -good
    0.41
    Good
    0.40
     GOOD
    0.39
     Faith
    0.38
     bad
    0.38
    .good
    0.34
    Activations Density 0.105%

    No Known Activations