© 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. 6-LLAMASCOPE-RES-32K
    11. 10773
    Prev
    Next
    INDEX
    Explanations

    references to death and mortality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Industrial
    -0.17
    1
    -0.16
    atura
    -0.16
    iaux
    -0.15
    7
    -0.15
    8
    -0.15
    annah
    -0.15
    2
    -0.15
    811
    -0.15
    DN
    -0.15
    POSITIVE LOGITS
    Ùģس
    0.15
    /browse
    0.15
     Leban
    0.15
    -ring
    0.15
    GLOSS
    0.15
    essian
    0.15
    /cop
    0.14
    Occurred
    0.14
     FactoryBot
    0.14
    à¸Īร
    0.14
    Activations Density 0.048%

    No Known Activations