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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 30-LLAMASCOPE-RES-32K
    11. 14914
    Prev
    Next
    INDEX
    Explanations

    phrases indicating emotional authenticity and personal growth experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oyo
    -0.15
    reon
    -0.14
    gili
    -0.13
     tÃŃch
    -0.13
    Inactive
    -0.13
    oya
    -0.13
    False
    -0.13
    лиÑĪ
    -0.13
     False
    -0.13
    owa
    -0.13
    POSITIVE LOGITS
     spontaneous
    0.46
     spont
    0.46
     improvis
    0.43
     improvised
    0.38
     spontaneously
    0.35
     improv
    0.35
     loose
    0.34
     random
    0.33
     informal
    0.33
     spur
    0.32
    Activations Density 0.569%

    No Known Activations