© 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. 12-LLAMASCOPE-RES-32K
    11. 16007
    Prev
    Next
    INDEX
    Explanations

    phrases encouraging engagement and anticipation for future content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enk
    -0.16
    strand
    -0.16
    chy
    -0.15
    ersistence
    -0.14
    odu
    -0.14
    ICES
    -0.14
    Äįek
    -0.14
    ãĥ³ãĥij
    -0.13
    ches
    -0.13
    nock
    -0.13
    POSITIVE LOGITS
     future
    0.17
     closely
    0.15
    éli
    0.15
    Destructor
    0.15
    ucker
    0.15
    à¹Ħว
    0.15
    future
    0.15
     developments
    0.14
    Transformer
    0.14
     ÙĨØ´
    0.14
    Activations Density 0.037%

    No Known Activations