© 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. 27-LLAMASCOPE-RES-32K
    11. 984
    Prev
    Next
    INDEX
    Explanations

    references to political promises and their fulfillment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     https
    -0.21
    =https
    -0.21
    Trump
    -0.20
     incel
    -0.20
     Brexit
    -0.20
     Manafort
    -0.20
     macOS
    -0.20
    -Trump
    -0.20
    202
    -0.20
     Patreon
    -0.19
    POSITIVE LOGITS
     Obama
    0.53
    Obama
    0.46
     Barack
    0.39
     Ob
    0.35
    Ob
    0.32
     OB
    0.28
     Obamacare
    0.27
     Ðŀб
    0.26
     stimulus
    0.26
     Stim
    0.26
    Activations Density 0.304%

    No Known Activations