© 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. 30-LLAMASCOPE-RES-32K
    6. 19050
    Prev
    Next
    INDEX
    Explanations

    concepts and discussions related to education and its various aspects, including institutions, policies, and practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Education
    -0.22
     education
    -0.22
    education
    -0.21
    æķĻèĤ²
    -0.20
     educate
    -0.20
     educated
    -0.20
    Education
    -0.19
     EDUC
    -0.19
     educational
    -0.18
     Educational
    -0.18
    POSITIVE LOGITS
    ally
    0.43
    ALLY
    0.31
    als
    0.29
     reform
    0.25
    /tr
    0.24
     attainment
    0.22
     Reform
    0.22
    ational
    0.21
    tainment
    0.20
    ainment
    0.20
    Activations Density 0.052%

    No Known Activations