INDEX

Explanations

instances of the letter 'g' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 placer

-0.15

.ibatis

-0.14

arkers

-0.14

 productive

-0.14

ÑĬ

-0.14

iversal

-0.13

allee

-0.13

 eyel

-0.13

myp

-0.13

rech

-0.13

POSITIVE LOGITS

bum

0.18

fh

0.16

.Areas

0.15

illion

0.15

ASSES

0.14

omik

0.14

vos

0.14

stack

0.13

Ø³Ø·

0.13

Activations Density 0.016%

instances of the letter 'g' in various contexts

No Comments

No Known Activations