© 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. 31-LLAMASCOPE-RES-32K
    11. 18740
    Prev
    Next
    INDEX
    Explanations

    terms that express the significance or importance of various concepts or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ø´ÙħاÙĦÛĮ
    -0.14
    Ñĸдно
    -0.14
    ymax
    -0.14
    _strerror
    -0.13
    burgh
    -0.13
     endif
    -0.13
    ÏĢει
    -0.13
    inese
    -0.12
     jadx
    -0.12
    ese
    -0.12
    POSITIVE LOGITS
     role
    0.78
     roll
    0.65
    role
    0.60
     roles
    0.59
    -role
    0.57
     rolls
    0.56
     Role
    0.56
     rol
    0.52
    Role
    0.50
     ROLE
    0.50
    Activations Density 0.066%

    No Known Activations