INDEX

Explanations

phrases indicating assistance or support 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 @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

akov

-0.19

Ð»ÐµÑĩ

-0.18

ield

-0.16

McB

-0.15

mel

-0.15

 diver

-0.14

.ErrorMessage

-0.14

Ð°ÐºÐ¾Ð²

-0.14

allow

-0.14

baum

-0.14

POSITIVE LOGITS

 matters

0.20

 Sticky

0.18

ÄĽk

0.17

aspect

0.16

Transition

0.16

Aspect

0.15

 aspect

0.15

iddy

0.15

 navigation

0.14

 zoekt

0.14

Activations Density 0.112%

phrases indicating assistance or support in various contexts

No Comments

No Known Activations