© 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. 23-LLAMASCOPE-RES-32K
    11. 12112
    Prev
    Next
    INDEX
    Explanations

    key terms and phrases related to medical instructions and patient communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ogle
    -0.15
     вÑĭбиÑĢа
    -0.15
     Ignore
    -0.14
     Já
    -0.14
    _ARGUMENT
    -0.13
    esian
    -0.13
    æį·
    -0.13
    zon
    -0.13
    -Ta
    -0.13
     ignore
    -0.13
    POSITIVE LOGITS
     chances
    0.22
     oft
    0.19
     often
    0.18
     Often
    0.18
     Odds
    0.17
     sometimes
    0.17
     Gauge
    0.17
     maybe
    0.17
     again
    0.17
    Often
    0.17
    Activations Density 0.151%

    No Known Activations