© 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. 15-LLAMASCOPE-RES-32K
    11. 4080
    Prev
    Next
    INDEX
    Explanations

    instances of quotation marks and their content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     “
    -0.26
     âĢŀ
    -0.25
    ãĢĮ
    -0.21
     ``
    -0.20
    ãĢĮãģĤ
    -0.19
    ãĢĮãģĬ
    -0.18
     ãĢĮ
    -0.18
     «
    -0.18
    “We
    -0.18
    “This
    -0.17
    POSITIVE LOGITS
    s
    0.16
    {'
    0.15
    ruba
    0.15
    rient
    0.15
    []"
    0.15
    gnore
    0.14
    alloca
    0.14
     Scalars
    0.13
    =~
    0.13
    ","",
    0.13
    Activations Density 0.643%

    No Known Activations