INDEX

Explanations

terms related to curvature or bending shapes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

æĵ¦

-0.18

 Ø¬ÙĦ

-0.16

onet

-0.16

amba

-0.16

ilden

-0.15

wargs

-0.15

quia

-0.15

aname

-0.15

à¸±à¸Ĺ

-0.15

utin

-0.15

POSITIVE LOGITS

weather

0.16

ulence

0.15

 weather

0.15

Ñİ

0.15

atters

0.15

arily

0.14

 Marilyn

0.14

ulent

0.14

yaw

0.14

ulous

0.14

Activations Density 0.041%

terms related to curvature or bending shapes

No Comments

No Known Activations