INDEX

Explanations

the repetition of the word 'more'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

porate

-0.18

imator

-0.16

hots

-0.15

Ð¾Ñĥ

-0.15

 numel

-0.15

osy

-0.14

dater

-0.14

orry

-0.14

SSIP

-0.14

nh

-0.14

POSITIVE LOGITS

alien

0.16

arton

0.15

irc

0.14

Ø§Ø¦Ø¬

0.14

oin

0.14

à¸µà¸¢à¸¡

0.14

ilin

0.14

erase

0.14

land

0.14

ramid

0.14

Activations Density 0.008%

the repetition of the word 'more'

No Comments

No Known Activations