INDEX

Explanations

qualifiers that intensify the degree of an adjective or adverb

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

olt

-0.16

ju

-0.15

ersen

-0.15

ner

-0.15

itian

-0.14

 countless

-0.14

*(*

-0.14

-0.13

pr

-0.13

dy

-0.13

POSITIVE LOGITS

dda

0.16

ANJI

0.16

ordum

0.15

.updateDynamic

0.15

owler

0.15

kees

0.15

/stdc

0.14

Ã¼ml

0.14

raci

0.14

Ã¡zd

0.14

Activations Density 0.019%

qualifiers that intensify the degree of an adjective or adverb

No Comments

No Known Activations