© 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. 1490
    Prev
    Next
    INDEX
    Explanations

    security-related concepts and discussions

    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
    iesz
    -0.13
    æī¶
    -0.13
    sian
    -0.13
    GAN
    -0.12
    esso
    -0.12
    ibles
    -0.12
    stub
    -0.12
    ä¹Ĺ
    -0.12
     ullam
    -0.12
    quette
    -0.11
    POSITIVE LOGITS
     security
    1.18
     Security
    1.02
    security
    0.98
    -security
    0.95
    Security
    0.94
     SECURITY
    0.87
    _security
    0.85
    .security
    0.78
    ecurity
    0.75
     secure
    0.74
    Activations Density 0.244%

    No Known Activations