© 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. 17112
    Prev
    Next
    INDEX
    Explanations

    references to sexual crimes and acts of sexual assault

    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
    anken
    -0.15
    antar
    -0.14
    ãĤıãģij
    -0.14
     hopefully
    -0.14
    ",__
    -0.14
    amas
    -0.14
    .XR
    -0.14
     siè
    -0.13
    pesan
    -0.13
     Beg
    -0.13
    POSITIVE LOGITS
     allegedly
    0.23
     approximately
    0.15
    ILLISE
    0.15
     Ñıк
    0.15
    582
    0.15
     purported
    0.15
    约
    0.15
     alleged
    0.14
     repeatedly
    0.14
    ower
    0.14
    Activations Density 0.402%

    No Known Activations