INDEX

Explanations

instances of the word "both."

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

Not in Any Lists

No Comments

Negative Logits

venture

-0.17

áº¡

-0.15

ceae

-0.14

ÐµÐ¶

-0.14

hin

-0.14

Ø´Ùħ

-0.14

 ÑĥÐ²

-0.13

ta

-0.13

of

-0.13

urovision

-0.13

POSITIVE LOGITS

inan

0.17

umann

0.16

Ã¶yle

0.16

Occurred

0.15

iei

0.14

chied

0.14

monic

0.14

gesch

0.14

 pant

0.14

Ã¤ÃŁ

0.14

Activations Density 0.015%

instances of the word "both."

No Comments

No Known Activations