© 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. 20-LLAMASCOPE-RES-32K
    11. 12611
    Prev
    Next
    INDEX
    Explanations

    phrases indicating refusal or rejection of actions

    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
    xbf
    -0.17
    alli
    -0.15
    uppe
    -0.15
    riba
    -0.14
    mutable
    -0.14
    mrt
    -0.14
    olic
    -0.14
    uala
    -0.14
     réuss
    -0.13
    apur
    -0.13
    POSITIVE LOGITS
     accept
    0.29
     accepting
    0.28
    accept
    0.27
     accepts
    0.26
     Accept
    0.25
    Accept
    0.23
    _accept
    0.22
     allow
    0.21
     acept
    0.21
     acceptance
    0.21
    Activations Density 0.127%

    No Known Activations