© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 16-LLAMASCOPE-RES-32K
    6. 6588
    Prev
    Next
    INDEX
    Explanations

    references to safety measures and protective devices related to security and health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahoo
    -0.16
     Shed
    -0.15
    orial
    -0.14
    GAN
    -0.14
     ilma
    -0.14
    itsu
    -0.14
    cce
    -0.14
    uelle
    -0.13
     آز
    -0.13
    scriptId
    -0.13
    POSITIVE LOGITS
     protection
    0.42
     protecting
    0.35
     protect
    0.34
     Protection
    0.33
    protect
    0.32
     protective
    0.32
     protects
    0.30
     Protect
    0.30
    ä¿ĿæĬ¤
    0.28
    ä¿ĿèŃ·
    0.28
    Activations Density 0.320%

    No Known Activations