© 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. 11855
    Prev
    Next
    INDEX
    Explanations

    terms related to counterproductive behaviors and concepts

    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
    .modules
    -0.14
     Dover
    -0.14
    axon
    -0.14
    ì§ĢëıĦ
    -0.13
    lessness
    -0.13
    862
    -0.13
    anced
    -0.13
     moderately
    -0.13
    átka
    -0.13
    anca
    -0.12
    POSITIVE LOGITS
    /null
    0.16
    usra
    0.16
    /problem
    0.15
     Hayden
    0.15
     pall
    0.15
    ieber
    0.14
    /dist
    0.14
    /false
    0.14
    ElementException
    0.14
    æİī
    0.14
    Activations Density 0.686%

    No Known Activations