INDEX

Explanations

instances of the letter 's' 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 @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ITIES

-0.18

hower

-0.17

Ð¶Ð´

-0.17

NSURLSession

-0.17

ingroup

-0.15

aeda

-0.15

zier

-0.14

ittle

-0.14

zeichnet

-0.14

altitude

-0.14

POSITIVE LOGITS

tab

0.23

pic

0.21

ved

0.21

kol

0.21

Ð²ÐµÐ¹

0.20

pag

0.20

pan

0.20

Ð²ÐµÐ´

0.20

wed

0.20

lif

0.20

Activations Density 0.009%

instances of the letter 's' in various contexts

No Comments

No Known Activations