© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 21-LLAMASCOPE-RES-32K
    11. 11641
    Prev
    Next
    INDEX
    Explanations

    references to memory and memorization-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elly
    -0.17
     disemb
    -0.15
    inel
    -0.14
    sek
    -0.14
    Ñįй
    -0.14
    annah
    -0.14
    -many
    -0.14
     Spencer
    -0.14
     comma
    -0.13
    ×ķ
    -0.13
    POSITIVE LOGITS
    brane
    0.32
    orial
    0.28
    cached
    0.24
    ories
    0.23
    orable
    0.22
    phis
    0.22
    antine
    0.20
    orious
    0.20
    BERS
    0.20
    ória
    0.18
    Activations Density 0.021%

    No Known Activations