© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-32K
    6. 19302
    Prev
    Next
    INDEX
    Explanations

    references to personal and professional backgrounds, particularly in relation to leadership and experiences in various sectors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ingen
    -0.17
    adoo
    -0.15
    /*č↵
    -0.15
    lass
    -0.14
    ToBounds
    -0.14
    anko
    -0.14
    edException
    -0.14
    xdc
    -0.14
    mtime
    -0.14
    deen
    -0.14
    POSITIVE LOGITS
     experience
    0.27
     understands
    0.24
     understand
    0.23
     understanding
    0.23
     knows
    0.22
     know
    0.22
     knowledge
    0.21
     Experience
    0.20
    ç»ıéªĮ
    0.20
    experience
    0.20
    Activations Density 0.287%

    No Known Activations