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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 28-LLAMASCOPE-RES-32K
    11. 26246
    Prev
    Next
    INDEX
    Explanations

    discussions around environmental issues and ethical dilemmas related to harm and responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åŃĿ
    -0.16
    \Abstract
    -0.15
    mony
    -0.14
    zac
    -0.14
    duk
    -0.14
    å¹»
    -0.13
    anzi
    -0.13
    ãģıãĤĮãĤĭ
    -0.13
     اØ
    -0.13
    zs
    -0.13
    POSITIVE LOGITS
     intentional
    0.76
     deliberate
    0.69
     intentionally
    0.62
     purpose
    0.58
     deliberately
    0.57
     conscious
    0.50
     purposely
    0.48
     Purpose
    0.48
    purpose
    0.48
     consciously
    0.47
    Activations Density 0.701%

    No Known Activations