© 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. 27-LLAMASCOPE-RES-32K
    11. 2111
    Prev
    Next
    INDEX
    Explanations

    phrases related to hazardous situations and potential injuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    污
    -0.15
    Äįan
    -0.15
    ãĥ¼ãĥģ
    -0.15
    Leaks
    -0.15
    Affected
    -0.14
    ãĥ¼ãĤ¿
    -0.14
    ipples
    -0.14
    ekim
    -0.14
    tml
    -0.14
    ),$
    -0.14
    POSITIVE LOGITS
     danger
    0.78
     dangerous
    0.73
     dangers
    0.71
    danger
    0.66
     Danger
    0.65
    -danger
    0.62
     Dangerous
    0.60
    Danger
    0.60
     hazardous
    0.60
     hazard
    0.58
    Activations Density 0.359%

    No Known Activations