© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 18-LLAMASCOPE-RES-32K
    11. 2301
    Prev
    Next
    INDEX
    Explanations

    elements related to health and safety regulations or standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nails
    -0.24
     nitrogen
    -0.23
     nose
    -0.22
     nurses
    -0.22
     Nurses
    -0.21
     Newton
    -0.21
     noodles
    -0.21
     nursing
    -0.21
     Nursing
    -0.21
     nervous
    -0.20
    POSITIVE LOGITS
    ieren
    0.14
    alist
    0.14
     gross
    0.14
    Surname
    0.14
     south
    0.14
    -o
    0.14
     din
    0.14
    works
    0.13
    CACHE
    0.13
    surname
    0.13
    Activations Density 0.254%

    No Known Activations