INDEX

Explanations

expressions related to transformation and recovery

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

OTA

-0.16

iq

-0.16

dip

-0.14

ota

-0.14

rics

-0.14

Éµ

-0.14

Ð¾Ð¿ÑĢÐ¸

-0.14

zier

-0.14

çħ§

-0.14

 Surprise

-0.13

POSITIVE LOGITS

 turn

0.44

 turned

0.42

turned

0.40

turn

0.40

 Turn

0.38

-turn

0.38

 TURN

0.36

.turn

0.35

 around

0.34

 turns

0.33

Activations Density 0.025%

expressions related to transformation and recovery

No Comments

No Known Activations