© 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. 9-LLAMASCOPE-RES-32K
    11. 23062
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ing" in various contexts, indicating ongoing actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pra
    -0.15
    unch
    -0.15
    krit
    -0.15
    .pix
    -0.14
    ãĥ¬ãĥ³
    -0.14
    okie
    -0.14
    iag
    -0.14
    ikan
    -0.14
    unami
    -0.14
    buquerque
    -0.14
    POSITIVE LOGITS
    ADIUS
    0.20
    iland
    0.17
    Verdana
    0.16
    pectrum
    0.14
    éľ
    0.14
    RefPtr
    0.14
    ¯u
    0.14
    sdale
    0.14
    804
    0.14
    inality
    0.14
    Activations Density 0.002%

    No Known Activations