INDEX

Explanations

references to experimental data and evaluation metrics

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ijkstra

-0.15

/javascript

-0.15

 Ð½Ð°ÑĢ

-0.14

(pdf

-0.14

Pdf

-0.14

á»ĭch

-0.13

 traps

-0.13

ulf

-0.13

 Lump

-0.13

POSITIVE LOGITS

 dataset

0.40

 datasets

0.35

dataset

0.33

 Dataset

0.33

.dataset

0.30

_dataset

0.29

Dataset

0.29

 benchmark

0.27

datasets

0.26

benchmark

0.26

Activations Density 0.101%

references to experimental data and evaluation metrics

No Comments

No Known Activations