© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-32K
    6. 1455
    Prev
    Next
    INDEX
    Explanations

    programming or technical terms related to data structures and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mojom
    -0.11
    åĨĴ
    -0.11
    _define
    -0.11
    osy
    -0.11
    .visitMethod
    -0.10
     åıĮ线
    -0.10
    .Buffered
    -0.10
    endir
    -0.10
    ½Ķëĵľ
    -0.10
    μιÏĥ
    -0.10
    POSITIVE LOGITS
     delete
    0.64
     Delete
    0.60
     deletion
    0.60
     deleting
    0.59
    delete
    0.58
     deletes
    0.58
     removal
    0.57
    Delete
    0.57
    åĪłéϤ
    0.57
     remove
    0.56
    Activations Density 0.932%

    No Known Activations