© 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. 16-LLAMASCOPE-RES-32K
    11. 5662
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to truth and transparency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ully
    -0.18
    sg
    -0.17
    alu
    -0.16
    sm
    -0.16
    otel
    -0.16
    AYS
    -0.15
    å¿Ĺ
    -0.15
     BÃł
    -0.15
    ati
    -0.15
    381
    -0.14
    POSITIVE LOGITS
    truth
    0.22
    Truth
    0.21
     truth
    0.21
     Truth
    0.20
    ãĥ³ãĤº
    0.18
    Expose
    0.18
    ÏģοÏį
    0.17
     truths
    0.17
     verdad
    0.17
     freeing
    0.16
    Activations Density 0.078%

    No Known Activations