© 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. 16874
    Prev
    Next
    INDEX
    Explanations

    references to medical qualifications and brain injuries

    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
     Skin
    -0.18
     skin
    -0.18
    Skin
    -0.16
    skin
    -0.16
    ocrine
    -0.15
     Native
    -0.15
    žÃŃ
    -0.15
    çĭIJ
    -0.14
    _skin
    -0.14
    egin
    -0.14
    POSITIVE LOGITS
     brain
    0.40
     Brain
    0.40
    brain
    0.36
    Brain
    0.35
     brains
    0.33
    Brains
    0.33
    èĦij
    0.31
     cere
    0.29
    brains
    0.28
     skull
    0.27
    Activations Density 0.086%

    No Known Activations