Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-32K
    6. 20706
    Prev
    Next
    INDEX
    Explanations

    phrases related to returning to a previous state or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    overy
    -0.16
    aul
    -0.14
    ær
    -0.14
    intval
    -0.14
    hani
    -0.14
    ää
    -0.14
    /ws
    -0.14
    ãĥªãĤ¢
    -0.14
    é¡
    -0.13
     Elias
    -0.13
    POSITIVE LOGITS
    upper
    0.17
     Chall
    0.15
    odo
    0.15
    cert
    0.15
    cken
    0.15
    caff
    0.14
     normals
    0.14
    imary
    0.14
    ivy
    0.14
    lane
    0.14
    Activations Density 0.098%

    No Known Activations