© 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. 25-LLAMASCOPE-RES-32K
    11. 16060
    Prev
    Next
    INDEX
    Explanations

    references to loved ones and expressions of love

    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
    iken
    -0.14
    à¹Ģà¸ĩ
    -0.14
    issy
    -0.14
    æĿIJ
    -0.14
    anco
    -0.14
     blame
    -0.14
    ad
    -0.14
    oro
    -0.13
    quoise
    -0.13
     پر
    -0.13
    POSITIVE LOGITS
     ones
    0.72
     Ones
    0.64
    ones
    0.60
    ONES
    0.42
    .ones
    0.34
    onest
    0.18
    onal
    0.17
     tw
    0.17
    ãĤĤãģ®
    0.17
     ons
    0.16
    Activations Density 0.012%

    No Known Activations