© 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. 20-LLAMASCOPE-RES-32K
    11. 29097
    Prev
    Next
    INDEX
    Explanations

    references to usernames, passwords, and email addresses within a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    akh
    -0.17
    onom
    -0.15
    gil
    -0.14
    ÐĿаÑģ
    -0.14
    rox
    -0.14
    achs
    -0.14
    imits
    -0.13
     wards
    -0.13
    oe
    -0.13
     Tamb
    -0.13
    POSITIVE LOGITS
    _assigned
    0.18
     used
    0.18
     assignments
    0.17
    ajas
    0.16
     Ùħبار
    0.16
    assigned
    0.16
    used
    0.16
    _ASSIGN
    0.15
    oproject
    0.15
    endas
    0.15
    Activations Density 0.217%

    No Known Activations