INDEX

Explanations

conjunctions and transitional phrases that indicate a continuation or shift in thought

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

amp

-0.17

AMP

-0.15

riter

-0.15

icari

-0.14

eger

-0.14

é¤Ĭ

-0.14

ooks

-0.14

Abe

-0.13

 Ware

-0.13

 convincing

-0.13

POSITIVE LOGITS

uzey

0.16

isContained

0.16

(EXPR

0.15

 Ø±Ø§ÛĮÚ¯Ø§ÙĨ

0.14

_resolve

0.14

usterity

0.14

istrovstvÃŃ

0.14

thane

0.13

_firestore

0.13

ä¸ĺ

0.13

Activations Density 1.251%

conjunctions and transitional phrases that indicate a continuation or shift in thought

No Comments

No Known Activations