INDEX

Explanations

the repeated use of the word "several."

oai_token-act-pair · gpt-4o-mini Triggered 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

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ses

-0.17

ãģĬãĤĬ

-0.16

rowsable

-0.15

ory

-0.15

 nÃ¤ch

-0.14

åĲĦç§į

-0.14

stuff

-0.14

osit

-0.14

 Certain

-0.14

frey

-0.14

POSITIVE LOGITS

 dozen

0.44

 hundred

0.38

 thousand

0.31

/all

0.25

-fold

0.25

 kinds

0.23

 Hundred

0.22

ty

0.22

 Ð´ÐµÑģÑıÑĤ

0.21

-times

0.20

Activations Density 0.025%

the repeated use of the word "several."

No Comments

No Known Activations