© 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. 17-LLAMASCOPE-RES-32K
    11. 5356
    Prev
    Next
    INDEX
    Explanations

    concepts related to memorable experiences and key moments in life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÑħÑĥ
    -0.16
    åIJ§
    -0.15
    uzz
    -0.14
    iego
    -0.14
    olec
    -0.14
     proh
    -0.14
    èo
    -0.14
    _ul
    -0.14
    Ñĥки
    -0.14
     telefon
    -0.13
    POSITIVE LOGITS
    ï¼ĮæīĢ以
    0.52
     therefore
    0.47
    æīĢ以
    0.45
     nên
    0.42
     Therefore
    0.42
     поÑįÑĤомÑĥ
    0.41
    ï¼ĮåĽłæѤ
    0.40
     hence
    0.40
     so
    0.39
    Therefore
    0.38
    Activations Density 1.164%

    No Known Activations