© 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. 20-LLAMASCOPE-RES-32K
    11. 16429
    Prev
    Next
    INDEX
    Explanations

    occurrences of self-reflection and admission in discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Closure
    -0.18
    ová
    -0.16
     Closure
    -0.16
    zÃŃ
    -0.16
    ätz
    -0.15
    iêu
    -0.15
     closure
    -0.14
     AssemblyCopyright
    -0.14
    ettel
    -0.14
    OVÃģ
    -0.14
    POSITIVE LOGITS
     admit
    0.82
     admitted
    0.80
     admission
    0.79
     admitting
    0.76
     admits
    0.73
     admissions
    0.68
     Admission
    0.64
     acknowledge
    0.57
     acknowledged
    0.54
     acknowledges
    0.53
    Activations Density 0.357%

    No Known Activations