© 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. 23-LLAMASCOPE-RES-32K
    11. 203
    Prev
    Next
    INDEX
    Explanations

    phrases indicating risks or hazards related to health and safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    جÙĪ
    -0.17
    isoft
    -0.16
    omap
    -0.16
    irty
    -0.16
    -à¤ħ
    -0.15
    acades
    -0.15
    reservation
    -0.15
    ');?>"
    -0.15
    iets
    -0.15
    shr
    -0.14
    POSITIVE LOGITS
    pose
    0.23
    idon
    0.23
     problems
    0.23
     challenges
    0.21
     questions
    0.21
     serious
    0.20
     threat
    0.19
     pose
    0.19
     challenge
    0.18
     risks
    0.18
    Activations Density 0.013%

    No Known Activations