© 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 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. 14811
    Prev
    Next
    INDEX
    Explanations

    incidents of injury or harm, particularly those involving negligence

    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
    adr
    -0.16
    /locale
    -0.15
    oca
    -0.14
    antic
    -0.14
     Hoy
    -0.14
    ارد
    -0.14
     Parr
    -0.13
    åħ
    -0.13
    abric
    -0.13
    ManagedObject
    -0.13
    POSITIVE LOGITS
     harm
    0.43
     injury
    0.42
     Harm
    0.36
     harmed
    0.35
     Injury
    0.35
     harms
    0.31
     injuries
    0.31
     hurt
    0.31
     injured
    0.30
     physical
    0.30
    Activations Density 0.141%

    No Known Activations