© 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. 27048
    Prev
    Next
    INDEX
    Explanations

    references to acts of violence, particularly murders and killings

    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
    879
    -0.15
     murderers
    -0.14
    roken
    -0.14
    anders
    -0.14
    ÃŃvel
    -0.13
    andest
    -0.13
     murderer
    -0.13
    éĽĦ
    -0.13
    iaz
    -0.13
    TypeInfo
    -0.13
    POSITIVE LOGITS
     innocent
    0.30
     innoc
    0.23
     Innoc
    0.21
     innocence
    0.20
    inn
    0.20
     unarmed
    0.20
     helpless
    0.19
     inoc
    0.18
     civilians
    0.17
     defense
    0.17
    Activations Density 0.131%

    No Known Activations