© 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. 26-LLAMASCOPE-RES-32K
    11. 7474
    Prev
    Next
    INDEX
    Explanations

    instances of suspicion or reports related to criminal activity or abuse

    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
     sill
    -0.15
    ạ
    -0.15
    UTOR
    -0.13
    solete
    -0.13
    lsa
    -0.13
    CREMENT
    -0.13
     Demonstr
    -0.13
    angu
    -0.13
    MBED
    -0.12
    zew
    -0.12
    POSITIVE LOGITS
     suspect
    0.95
     Sus
    0.90
     suspects
    0.88
    sus
    0.86
     suspicion
    0.84
     sus
    0.82
    Sus
    0.82
     Susp
    0.81
    Susp
    0.79
     suspicious
    0.77
    Activations Density 0.244%

    No Known Activations