© 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 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. 19-LLAMASCOPE-RES-32K
    11. 4350
    Prev
    Next
    INDEX
    Explanations

    mentions of people and their roles in social contexts or group dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     finally
    -0.16
    Recently
    -0.15
     recently
    -0.15
    iaux
    -0.15
     Recently
    -0.14
     ultimately
    -0.14
     finished
    -0.14
    hti
    -0.14
    iais
    -0.14
     lately
    -0.14
    POSITIVE LOGITS
     immediately
    0.52
     immediate
    0.40
     instantly
    0.39
     Immediately
    0.38
     ÑģÑĢазÑĥ
    0.37
     immedi
    0.36
     sofort
    0.32
     Immediate
    0.31
    ç«ĭåĪ»
    0.30
    mediately
    0.28
    Activations Density 0.266%

    No Known Activations