© 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. 25-LLAMASCOPE-RES-32K
    11. 32708
    Prev
    Next
    INDEX
    Explanations

    phrases related to morality and social hierarchy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     basically
    -0.17
     ditch
    -0.16
    zzo
    -0.16
    iglia
    -0.16
     weren
    -0.15
     decided
    -0.15
    SupportActionBar
    -0.15
     essentially
    -0.14
    /latest
    -0.14
    spl
    -0.14
    POSITIVE LOGITS
     addict
    0.17
     trem
    0.16
     intr
    0.16
     consent
    0.16
     THINK
    0.15
     labor
    0.15
     Verfüg
    0.15
     av
    0.15
     advert
    0.15
     labour
    0.15
    Activations Density 0.334%

    No Known Activations