© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6271
    Prev
    Next
    INDEX
    Explanations

    concepts related to morality and ethics

    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
    ulong
    -0.16
     пÑĢоÑĢ
    -0.15
     Burr
    -0.14
    ertino
    -0.14
    biz
    -0.14
    ekk
    -0.14
    å¹ķ
    -0.14
    oten
    -0.14
    -solid
    -0.14
    uyá»ģn
    -0.14
    POSITIVE LOGITS
     Ses
    0.17
    _support
    0.17
    esa
    0.16
     Ocean
    0.15
     sesame
    0.15
     Sud
    0.15
     rád
    0.15
     Cyan
    0.15
    ̣
    0.15
    梨
    0.15
    Activations Density 0.054%

    No Known Activations