© 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. 11-LLAMASCOPE-RES-32K
    11. 29857
    Prev
    Next
    INDEX
    Explanations

    various types of categories or classification marks in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ombs
    -0.16
    prus
    -0.16
    743
    -0.15
    _UNUSED
    -0.15
    uma
    -0.14
    bay
    -0.14
    739
    -0.14
    issing
    -0.14
     оÑĤв
    -0.14
    zeÅĪ
    -0.14
    POSITIVE LOGITS
    ãĥ¼ãĥĬ
    0.14
    inality
    0.14
    struk
    0.14
    å´
    0.14
     cutter
    0.14
     Roose
    0.14
     Hernandez
    0.14
    -ie
    0.13
    iang
    0.13
     Ear
    0.13
    Activations Density 0.037%

    No Known Activations