INDEX

Explanations

phrases emphasizing quantity or repetition of items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

egas

-0.18

echa

-0.15

aspers

-0.15

edis

-0.15

Ð¶Ñĥ

-0.14

bid

-0.14

Ø§Ø´Ø©

-0.13

abile

-0.13

erner

-0.13

jadi

-0.13

POSITIVE LOGITS

Tos

0.16

lh

0.16

Ã³d

0.15

0.14

ammer

0.14

ivil

0.14

ody

0.14

beit

0.13

amel

0.13

 inherits

0.13

Activations Density 0.020%

phrases emphasizing quantity or repetition of items

No Comments

No Known Activations