© 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. 26-LLAMASCOPE-RES-32K
    11. 1188
    Prev
    Next
    INDEX
    Explanations

    terms related to sentencing and legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ardy
    -0.18
    oge
    -0.18
    ulis
    -0.16
    íĢ
    -0.16
     lawsuit
    -0.16
     lawsuits
    -0.15
     Widow
    -0.15
    imler
    -0.15
    lash
    -0.15
    ç·Ĭ
    -0.15
    POSITIVE LOGITS
     Sent
    0.41
    Sent
    0.38
     sentence
    0.38
    sent
    0.37
     sentences
    0.35
     Sentence
    0.33
     SENT
    0.32
     sentencing
    0.32
    sentence
    0.31
    .sent
    0.30
    Activations Density 0.035%

    No Known Activations