© 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. 10914
    Prev
    Next
    INDEX
    Explanations

    quotes and phrases about morality and purpose

    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
    ehr
    -0.16
    coni
    -0.15
    abyrin
    -0.14
    zej
    -0.14
    iley
    -0.14
    ÑĥÑĤи
    -0.14
    äs
    -0.14
    cury
    -0.13
    468
    -0.13
    ologne
    -0.13
    POSITIVE LOGITS
    ieu
    0.14
     Gratuit
    0.14
    俺ãģ¯
    0.13
    orderid
    0.13
     Cham
    0.13
    èo
    0.13
     Ham
    0.13
     ~
    0.13
     Medi
    0.13
    飯
    0.12
    Activations Density 0.305%

    No Known Activations