INDEX

Explanations

words related to performance and action 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 @ 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

isque

-0.16

åĲĲ

-0.14

 Piet

-0.14

 unre

-0.14

Ã£n

-0.14

Ã©rer

-0.13

rv

-0.13

 Needle

-0.13

edla

-0.13

POSITIVE LOGITS

ovich

0.17

oldem

0.17

hari

0.16

ERGE

0.16

 maturity

0.14

hl

0.14

HER

0.14

 Ð³ÐµÑĢ

0.13

sez

0.13

 Morav

0.13

Activations Density 0.023%

words related to performance and action in various contexts

No Comments

No Known Activations