© 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. 4-LLAMASCOPE-RES-32K
    6. 30332
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize various interpretations of the concept of meaning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agna
    -0.18
    etry
    -0.16
    iran
    -0.15
    ÑĢави
    -0.14
    Temporal
    -0.14
    /lists
    -0.13
     Merk
    -0.13
    ack
    -0.13
    741
    -0.13
    achu
    -0.13
    POSITIVE LOGITS
     meaning
    0.17
    fully
    0.17
    $MESS
    0.17
    AndHashCode
    0.16
     meanings
    0.15
    nes
    0.15
    Ðĥ
    0.15
    nings
    0.14
    úi
    0.14
    FUL
    0.14
    Activations Density 0.029%

    No Known Activations