© 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. 21-LLAMASCOPE-RES-32K
    11. 8218
    Prev
    Next
    INDEX
    Explanations

    references to political promises and practices that involve spending and regulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ansi
    -0.17
    atar
    -0.14
    ans
    -0.14
    طار
    -0.14
    ÏģÏī
    -0.14
    ANS
    -0.13
    .openConnection
    -0.13
    aison
    -0.13
    aeda
    -0.13
    ought
    -0.13
    POSITIVE LOGITS
     practice
    0.78
    practice
    0.68
     practise
    0.61
    Practice
    0.59
     Practice
    0.58
     practices
    0.55
     Practices
    0.47
     technique
    0.44
     habit
    0.44
     pratique
    0.43
    Activations Density 0.358%

    No Known Activations