INDEX

Explanations

references to "bar," particularly in various contexts or phrases

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

erver

-0.18

erson

-0.17

atsu

-0.16

ska

-0.16

ency

-0.15

eling

-0.15

imple

-0.15

erv

-0.14

naire

-0.14

arring

-0.14

POSITIVE LOGITS

resi

0.18

riers

0.16

AGMA

0.16

riere

0.15

oque

0.15

riÃ¨re

0.15

Ø±

0.15

agg

0.15

asan

0.15

illions

0.15

Activations Density 0.042%

references to "bar," particularly in various contexts or phrases

No Known Activations