INDEX

Explanations

references to knitting activities and related projects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 Haut

-0.16

(ConfigurationManager

-0.15

å¸

-0.14

 shaving

-0.14

paper

-0.13

 wood

-0.13

 jack

-0.13

ieu

-0.13

imitives

-0.13

 etiqu

-0.13

POSITIVE LOGITS

 knitting

0.24

 cables

0.23

 pattern

0.23

 Gauge

0.23

 Cable

0.22

 knit

0.22

.Pattern

0.21

 cable

0.21

 Pattern

0.21

Pattern

0.20

Activations Density 0.028%

references to knitting activities and related projects

No Comments

No Known Activations