© 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. 19-LLAMASCOPE-RES-32K
    11. 29732
    Prev
    Next
    INDEX
    Explanations

    vulnerabilities and exposure to risks, particularly in the context of security and safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nero
    -0.14
    ocide
    -0.14
    onders
    -0.14
     Rowe
    -0.14
    ante
    -0.14
    íķŃ
    -0.14
    kud
    -0.14
    formance
    -0.13
    íĨł
    -0.13
     benef
    -0.13
    POSITIVE LOGITS
     vulnerability
    0.57
     vulnerable
    0.56
     Vulner
    0.54
     susceptible
    0.49
     susceptibility
    0.48
     vulnerabilities
    0.46
     vulner
    0.44
     suscept
    0.43
     prone
    0.34
     unprotected
    0.32
    Activations Density 0.218%

    No Known Activations