© 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. 17-LLAMASCOPE-RES-32K
    11. 26220
    Prev
    Next
    INDEX
    Explanations

    references to nudity or being naked

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fried
    -0.16
    kle
    -0.15
    erras
    -0.15
    Ìĥ
    -0.15
    rides
    -0.15
    azes
    -0.14
    agal
    -0.14
    ầm
    -0.14
    eprom
    -0.14
     skirts
    -0.14
    POSITIVE LOGITS
    /raw
    0.23
     bare
    0.22
     Naked
    0.21
     naked
    0.20
    bare
    0.20
    /null
    0.18
     revealed
    0.17
    .githubusercontent
    0.17
    bones
    0.17
    ness
    0.17
    Activations Density 0.019%

    No Known Activations