© 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. 22-LLAMASCOPE-RES-32K
    11. 3964
    Prev
    Next
    INDEX
    Explanations

    references to adult content or pornography

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĢ¦↵
    -0.17
     âĢ¦↵
    -0.15
    âĢ¦↵↵
    -0.13
    âĢ¦âĢ¦
    -0.13
     [âĢ¦]↵
    -0.13
    âĢ¦âĢ¦↵↵
    -0.12
     hoa
    -0.11
    XXXXXXXX
    -0.11
     âĢ¦.
    -0.11
    iscard
    -0.11
    POSITIVE LOGITS
    .scalablytyped
    0.15
    ROTO
    0.14
    /DTD
    0.14
    Âłin
    0.14
    ">//
    0.13
    /Dk
    0.13
    ¨ë¶Ģ
    0.12
    swire
    0.12
    oại
    0.12
    #
    0.12
    Activations Density 9.284%

    No Known Activations