INDEX

Explanations

repeated occurrences of the word "Gr."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

raf

-0.16

straint

-0.16

-0.15

raph

-0.14

asdf

-0.14

weis

-0.14

iversal

-0.14

å½¹

-0.14

itler

-0.13

POSITIVE LOGITS

gr

0.26

Gr

0.23

-gr

0.22

/gr

0.22

.gr

0.22

(gr

0.20

GR

0.19

gr

0.19

.Gr

0.18

Gr

0.17

Activations Density 0.018%

repeated occurrences of the word "Gr."

No Comments

No Known Activations