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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 30-LLAMASCOPE-RES-32K
    11. 2930
    Prev
    Next
    INDEX
    Explanations

    terms related to cybersecurity threats and vulnerabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CAD
    -0.15
    uai
    -0.14
    inh
    -0.14
     tower
    -0.14
     interpret
    -0.14
    fas
    -0.14
    æ¬
    -0.13
     leh
    -0.13
    rott
    -0.13
    isodes
    -0.13
    POSITIVE LOGITS
     Fancy
    0.26
    APT
    0.23
     operation
    0.22
     campaigns
    0.22
     Operation
    0.21
     actor
    0.21
     Lazar
    0.21
     attribution
    0.20
     actors
    0.19
     campaign
    0.19
    Activations Density 0.159%

    No Known Activations