© 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. 31-LLAMASCOPE-RES-32K
    11. 492
    Prev
    Next
    INDEX
    Explanations

    medical symptoms and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avern
    -0.15
     заболева
    -0.15
    idden
    -0.15
    iphy
    -0.14
    bjerg
    -0.14
    oba
    -0.14
    é¾Ħ
    -0.14
    åĤ·
    -0.14
    ismatch
    -0.14
    uche
    -0.14
    POSITIVE LOGITS
     weakness
    0.30
     difficulty
    0.29
     fatigue
    0.29
     blurred
    0.28
     loss
    0.26
     vomiting
    0.26
     nausea
    0.26
     muscle
    0.25
     confusion
    0.25
     decreased
    0.25
    Activations Density 0.098%

    No Known Activations