INDEX

Explanations

occurrences of the word "last" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

oretical

-0.17

rch

-0.14

rum

-0.14

uchs

-0.14

 ì¹ľ

-0.13

 arithmetic

-0.13

ampler

-0.13

 handed

-0.13

prit

-0.13

ä¹ĭ

-0.13

POSITIVE LOGITS

 year

0.27

year

0.21

.year

0.18

decade

0.18

 week

0.18

å¹´ãģ®

0.16

 years

0.16

 century

0.16

 Ð³Ð¾Ð´Ñĥ

0.16

å¹´

0.15

Activations Density 0.025%

occurrences of the word "last" in various contexts

No Comments

No Known Activations