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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 27-LLAMASCOPE-RES-32K
    11. 12664
    Prev
    Next
    INDEX
    Explanations

    descriptors related to quality in handmade products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    entiful
    -0.15
    ORMAT
    -0.15
    anca
    -0.15
    avis
    -0.15
    orny
    -0.14
    OMUX
    -0.14
    istrovstvÃŃ
    -0.14
    PÅĻ
    -0.14
     ÃŃch
    -0.14
    INGTON
    -0.14
    POSITIVE LOGITS
     quality
    0.29
     Quality
    0.26
    quality
    0.24
    Quality
    0.24
     guarantee
    0.23
     hand
    0.22
     attention
    0.21
     rigorous
    0.21
     guarantees
    0.20
     ensure
    0.19
    Activations Density 0.310%

    No Known Activations