© 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. 16-LLAMASCOPE-RES-32K
    11. 8062
    Prev
    Next
    INDEX
    Explanations

    references to potential dangers or threats

    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
    .modules
    -0.16
    /pdf
    -0.14
    ãģ³
    -0.13
    ocker
    -0.13
    961
    -0.13
    stood
    -0.13
     apparent
    -0.13
    ÏĦαÏĤ
    -0.13
     dr
    -0.13
     nearly
    -0.13
    POSITIVE LOGITS
     kdyby
    0.19
     potentially
    0.18
    might
    0.17
    possibly
    0.17
     Might
    0.16
    æĪĸèĢħ
    0.16
     Harm
    0.16
     possibly
    0.16
     might
    0.16
    ogle
    0.15
    Activations Density 0.218%

    No Known Activations