INDEX

Explanations

instances of comparisons or contrasts in the text

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 Mountain

-0.15

ads

-0.15

imitives

-0.14

Ãº

-0.14

anki

-0.14

gi

-0.14

 Freder

-0.13

 Wings

-0.13

ama

-0.13

POSITIVE LOGITS

Helmet

0.15

ê»ĺ

0.15

nodoc

0.14

beck

0.14

å®¢

0.14

tron

0.13

ullet

0.13

AVR

0.13

Sac

0.13

cf

0.13

Activations Density 0.110%

instances of comparisons or contrasts in the text

No Comments

No Known Activations