© 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. 11-LLAMASCOPE-RES-32K
    11. 7602
    Prev
    Next
    INDEX
    Explanations

    expressions indicating dishonesty or manipulation in contexts of work or societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ikk
    -0.15
    enville
    -0.14
    eer
    -0.14
    uki
    -0.14
    ycastle
    -0.14
    loon
    -0.14
    byn
    -0.14
    ازÙĦ
    -0.13
    uku
    -0.13
     (*(
    -0.13
    POSITIVE LOGITS
     Vice
    0.18
    vice
    0.17
     vice
    0.17
    alem
    0.16
    hait
    0.15
     Secondary
    0.14
    hof
    0.14
    Ïģγ
    0.14
     Representative
    0.14
    .setViewportView
    0.14
    Activations Density 0.083%

    No Known Activations