INDEX

Explanations

instances of the word "chop" and its variations in different contexts

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

-0.25

er

-0.18

yb

-0.18

yar

-0.16

ichten

-0.16

ey

-0.16

YM

-0.15

yw

-0.15

le

-0.15

oubted

-0.15

POSITIVE LOGITS

py

0.28

pen

0.24

portunity

0.23

pi

0.21

inions

0.21

pler

0.21

engl

0.20

kins

0.20

posite

0.18

inion

0.18

Activations Density 0.027%

instances of the word "chop" and its variations in different contexts

No Comments

No Known Activations