INDEX

Explanations

references to dress codes and types of clothing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

bsolute

-0.18

edu

-0.17

hq

-0.15

ave

-0.14

ame

-0.14

ornings

-0.14

ergic

-0.14

opers

-0.14

bis

-0.13

 Hardy

-0.13

POSITIVE LOGITS

ses

0.24

 rehearsal

0.23

maker

0.20

sed

0.20

oir

0.19

(es

0.18

makers

0.18

 rehears

0.18

ings

0.18

ler

0.17

Activations Density 0.013%

references to dress codes and types of clothing

No Comments

No Known Activations