© 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. 24-LLAMASCOPE-RES-32K
    11. 21467
    Prev
    Next
    INDEX
    Explanations

    references to government programs and oversight related to public health and safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aign
    -0.17
    tere
    -0.14
    _predicted
    -0.14
    stral
    -0.14
    GIT
    -0.13
    _AB
    -0.13
     incompetence
    -0.13
    iç
    -0.13
    itt
    -0.13
    Predict
    -0.13
    POSITIVE LOGITS
     congressional
    0.17
    adero
    0.17
     Congressional
    0.15
    holm
    0.15
     Congress
    0.15
    DATES
    0.15
    ugo
    0.14
     FDA
    0.14
    OMB
    0.14
    conc
    0.14
    Activations Density 0.013%

    No Known Activations