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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 10-LLAMASCOPE-RES-32K
    11. 22961
    Prev
    Next
    INDEX
    Explanations

    words related to support and safety measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    indre
    -0.16
    omanip
    -0.15
    uese
    -0.15
    basis
    -0.14
    kok
    -0.14
     buc
    -0.14
    alice
    -0.14
    beg
    -0.14
    jom
    -0.14
     gid
    -0.14
    POSITIVE LOGITS
     æĸ
    0.15
     Boundary
    0.15
    ointed
    0.15
    264
    0.14
     Ens
    0.14
    ä¸Ī
    0.14
    246
    0.14
    444
    0.14
    515
    0.14
    chwitz
    0.14
    Activations Density 0.036%

    No Known Activations