© 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. 11-LLAMASCOPE-RES-32K
    11. 20672
    Prev
    Next
    INDEX
    Explanations

    references to laws and principles regarding morality and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uien
    -0.16
    dux
    -0.16
    inent
    -0.15
    fone
    -0.15
    ERA
    -0.14
    .spin
    -0.14
     Sikh
    -0.14
    INED
    -0.14
    agon
    -0.14
    mdb
    -0.14
    POSITIVE LOGITS
    951
    0.16
     Burl
    0.16
    avra
    0.16
    aver
    0.14
    ayar
    0.14
    ipi
    0.14
    'gc
    0.14
    arest
    0.14
    autorelease
    0.14
     warning
    0.14
    Activations Density 0.205%

    No Known Activations