INDEX

Explanations

verbs that express statements or claims

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

eg

-0.16

arr

-0.14

stry

-0.14

 {{--<

-0.14

agger

-0.13

 Reid

-0.13

URL

-0.13

Hag

-0.13

POSITIVE LOGITS

lest

0.17

 cÃ©lib

0.16

ìĦľëĬĶ

0.16

ayi

0.15

chÃ©

0.15

nants

0.15

 EXEMPLARY

0.15

jer

0.15

èĪį

0.15

ije

0.14

Activations Density 0.047%

verbs that express statements or claims

No Comments

No Known Activations