© 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. 2-LLAMASCOPE-RES-32K
    11. 6210
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "di" which likely refers to a preposition in Italian

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    latin
    -0.15
    ãĥ¼ãĥª
    -0.15
    odore
    -0.15
    irt
    -0.15
    loom
    -0.15
    orizontal
    -0.14
    s
    -0.14
    oven
    -0.14
    anean
    -0.14
    oin
    -0.14
    POSITIVE LOGITS
    imuth
    0.15
    richt
    0.14
    LOCKS
    0.14
    urnal
    0.14
     Boo
    0.14
     lens
    0.14
     Gale
    0.14
    ãģĵãģĿ
    0.14
    ¼
    0.13
    isted
    0.13
    Activations Density 0.005%

    No Known Activations