INDEX

Explanations

comparisons emphasizing superiority or preference

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

atism

-0.17

erken

-0.15

endez

-0.14

anzi

-0.14

ypad

-0.14

amÄ±z

-0.14

IQUE

-0.13

ç°

-0.13

Ð¾Ð´Ð¸

-0.13

POSITIVE LOGITS

 anywhere

0.16

aram

0.15

aira

0.15

 rarely

0.14

hone

0.14

arga

0.14

 than

0.14

Ø³ØªÛĮ

0.14

_ALLOW

0.14

 imposs

0.14

Activations Density 0.046%

comparisons emphasizing superiority or preference

No Comments

No Known Activations