© 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. 9-LLAMASCOPE-RES-32K
    11. 19931
    Prev
    Next
    INDEX
    Explanations

    references to safety and safety-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    serter
    -0.16
    oha
    -0.15
    sto
    -0.15
    lets
    -0.15
    éis
    -0.14
    ApplicationContext
    -0.14
    ao
    -0.14
    û
    -0.14
     dõi
    -0.14
    ç±į
    -0.14
    POSITIVE LOGITS
    tainment
    0.18
    /security
    0.17
    ron
    0.15
    bast
    0.14
    ably
    0.14
    acious
    0.14
     Hurricane
    0.14
    ebi
    0.14
    RON
    0.14
    andre
    0.14
    Activations Density 0.035%

    No Known Activations