© 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. 22539
    Prev
    Next
    INDEX
    Explanations

    phrases that include the conjunction "and" and variations of it

    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
     whereas
    -0.16
    islav
    -0.13
    iner
    -0.13
     pÅĻiÄįemž
    -0.13
    alim
    -0.12
     ÙĪاÙĦتÙĬ
    -0.12
    :↵
    -0.12
    itech
    -0.12
    lernen
    -0.12
     Angiospermae
    -0.12
    POSITIVE LOGITS
    ients
    0.32
    /or
    0.28
     indeed
    0.25
     especially
    0.24
     оÑģобенно
    0.20
    uxtap
    0.20
    оÑģоб
    0.19
    phans
    0.19
    especially
    0.18
     even
    0.18
    Activations Density 0.302%

    No Known Activations