INDEX

Explanations

phrases indicating effort or action taken to improve a situation

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

 Brushes

-0.15

glob

-0.15

amaz

-0.15

+)/

-0.15

ixer

-0.14

TOD

-0.14

Ð¨ÐĲ

-0.14

ush

-0.14

oad

-0.14

ukes

-0.14

POSITIVE LOGITS

.scalablytyped

0.17

'gc

0.15

0.14

ollah

0.14

jian

0.14

ifacts

0.14

issent

0.14

ecko

0.14

 Falk

0.14

rawn

0.14

Activations Density 0.008%

phrases indicating effort or action taken to improve a situation

No Comments

No Known Activations