© 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. 29-LLAMASCOPE-RES-32K
    11. 2616
    Prev
    Next
    INDEX
    Explanations

    expressions of personal preference and comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tep
    -0.16
    witter
    -0.16
    ëĨ
    -0.15
    setw
    -0.14
    ç·Ĵ
    -0.14
    ÑĢиÑģ
    -0.14
    iguiente
    -0.14
    roupon
    -0.13
    agle
    -0.13
    ham
    -0.13
    POSITIVE LOGITS
     prefer
    1.06
     preference
    1.03
     preferred
    0.92
     Prefer
    0.91
     Preference
    0.90
     preferences
    0.87
     prefers
    0.87
    prefer
    0.86
    Preference
    0.79
     пÑĢедпоÑĩ
    0.79
    Activations Density 0.648%

    No Known Activations