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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-32K
    11. 18706
    Prev
    Next
    INDEX
    Explanations

    terms related to device security and monitoring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éri
    -0.17
    hores
    -0.15
    IRMWARE
    -0.15
    anus
    -0.14
     OMIT
    -0.14
    LLU
    -0.13
    upd
    -0.13
    æĽ¸é¤¨
    -0.13
    _hor
    -0.13
    remen
    -0.13
    POSITIVE LOGITS
     detected
    0.23
    æ£Ģæµĭ
    0.18
     Detected
    0.17
    lings
    0.17
     mere
    0.16
     abnormal
    0.16
     signal
    0.15
     movement
    0.15
     presence
    0.15
     detecting
    0.15
    Activations Density 0.059%

    No Known Activations