© 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. 26-LLAMASCOPE-RES-32K
    11. 10993
    Prev
    Next
    INDEX
    Explanations

    references to surveillance technology and facial recognition systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gnore
    -0.15
     vandal
    -0.14
    _SUPPORTED
    -0.14
    ocide
    -0.14
     Wheels
    -0.13
    loff
    -0.13
    zar
    -0.13
    _HT
    -0.13
    /layouts
    -0.13
    sein
    -0.13
    POSITIVE LOGITS
     surveillance
    0.39
     privacy
    0.36
     Surveillance
    0.32
     Privacy
    0.31
     surve
    0.29
    privacy
    0.28
    Privacy
    0.28
     sno
    0.27
     tracking
    0.27
     spy
    0.26
    Activations Density 0.204%

    No Known Activations