© 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. 20-LLAMASCOPE-RES-32K
    11. 23470
    Prev
    Next
    INDEX
    Explanations

    code formatting and mathematical expressions

    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
    eda
    -0.16
     å²
    -0.16
    qm
    -0.15
    inker
    -0.14
    iece
    -0.14
    ook
    -0.13
     Moh
    -0.13
    rowsers
    -0.13
    orth
    -0.13
    ocket
    -0.13
    POSITIVE LOGITS
    uiten
    0.16
     Spir
    0.14
    iyat
    0.14
    PLIC
    0.14
    er
    0.14
    _IL
    0.14
    .ra
    0.14
    _foreign
    0.14
    avers
    0.13
    uen
    0.13
    Activations Density 0.010%

    No Known Activations