© 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. 16-LLAMASCOPE-RES-32K
    11. 5254
    Prev
    Next
    INDEX
    Explanations

    terms related to investigations and inquiries into legal or ethical violations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acket
    -0.15
    ADI
    -0.14
    ollect
    -0.14
    одеÑĢж
    -0.14
    032
    -0.14
    obra
    -0.13
     Trib
    -0.13
     smugg
    -0.13
    éłħ
    -0.13
    olec
    -0.13
    POSITIVE LOGITS
     whether
    0.22
    æĺ¯åIJ¦
    0.18
     possible
    0.17
    åĪ°åºķ
    0.16
     allegations
    0.16
     Whether
    0.16
    ugi
    0.16
    åĨĮ
    0.16
     allegation
    0.15
     possibly
    0.15
    Activations Density 0.085%

    No Known Activations