© 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. 18-LLAMASCOPE-RES-32K
    11. 25022
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal concepts and proceedings, particularly those involving defamation and reputation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Grass
    -0.15
    erals
    -0.15
    abez
    -0.15
     åįİ
    -0.15
     Cove
    -0.14
    fov
    -0.14
    itan
    -0.14
     coder
    -0.14
    inally
    -0.13
    åįİ
    -0.13
    POSITIVE LOGITS
    -negative
    0.20
     negative
    0.19
     gossip
    0.18
    åĮ
    0.17
     inn
    0.17
    accuracy
    0.17
     inaccur
    0.17
     smear
    0.17
     Accuracy
    0.17
     Lies
    0.17
    Activations Density 0.112%

    No Known Activations