© 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. 22-LLAMASCOPE-RES-32K
    11. 27596
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to authority and conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osaic
    -0.15
     boyc
    -0.14
     RESERVED
    -0.14
    reserved
    -0.14
    ulus
    -0.14
    loub
    -0.14
    @mail
    -0.14
     refusal
    -0.14
    ibold
    -0.14
    å´
    -0.14
    POSITIVE LOGITS
     control
    0.26
     eliminate
    0.23
     qu
    0.23
     sil
    0.23
     stop
    0.23
     cur
    0.22
    æĬij
    0.22
     curb
    0.22
    -control
    0.22
     suppression
    0.22
    Activations Density 0.094%

    No Known Activations