© 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. 25-LLAMASCOPE-RES-32K
    11. 16032
    Prev
    Next
    INDEX
    Explanations

    phrases beginning with "under," indicating discussions of conditions, circumstances, or policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OLL
    -0.16
    okit
    -0.16
    usercontent
    -0.16
    ilter
    -0.16
    бÑĢа
    -0.15
    LOCKS
    -0.15
    ffective
    -0.15
    unas
    -0.14
     sobie
    -0.14
    okane
    -0.14
    POSITIVE LOGITS
    neath
    0.27
     ausp
    0.27
    lying
    0.27
    lining
    0.26
     circumstances
    0.23
    lined
    0.23
     terms
    0.23
    pin
    0.22
    p
    0.20
    graduate
    0.20
    Activations Density 0.046%

    No Known Activations