© 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. 28-LLAMASCOPE-RES-32K
    11. 264
    Prev
    Next
    INDEX
    Explanations

    references to travel and transportation challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ipples
    -0.16
    æļĸ
    -0.16
    plib
    -0.15
    ëĿ½
    -0.15
    hek
    -0.15
    æĤ²
    -0.14
    ivent
    -0.14
    eref
    -0.13
    Unchecked
    -0.13
    629
    -0.13
    POSITIVE LOGITS
     hostile
    0.34
     dangerous
    0.33
     difficult
    0.33
     challenging
    0.32
     hazardous
    0.30
     unfamiliar
    0.29
     inh
    0.28
     rough
    0.28
     unknown
    0.27
     adverse
    0.27
    Activations Density 0.254%

    No Known Activations