© 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. 24-LLAMASCOPE-RES-32K
    11. 15714
    Prev
    Next
    INDEX
    Explanations

    occurrences of personal pronouns and phrases indicative of human interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nepÅĻÃŃ
    -0.16
     máºŃt
    -0.15
    essel
    -0.14
     deprivation
    -0.14
     depr
    -0.14
     derec
    -0.14
     heed
    -0.14
     Forgot
    -0.13
     ignorance
    -0.13
     shorten
    -0.13
    POSITIVE LOGITS
     slow
    0.54
     slower
    0.50
     slowed
    0.49
     Slow
    0.49
    Slow
    0.47
    slow
    0.46
     delay
    0.44
     Delay
    0.44
    delay
    0.44
    Delay
    0.44
    Activations Density 0.017%

    No Known Activations