INDEX

Explanations

phrases and questions that express degrees of awareness or understanding about a situation or subject

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

pt

-0.15

plus

-0.14

@a

-0.14

inning

-0.14

 Eins

-0.14

jon

-0.13

 will

-0.13

qv

-0.13

tember

-0.13

pte

-0.13

POSITIVE LOGITS

ãģĭãĤı

0.25

akin

0.18

itzer

0.16

edn

0.16

ļ

0.16

--)↵

0.15

Ëĺ

0.15

Falsy

0.15

 miÃªu

0.15

emand

0.15

Activations Density 0.046%

phrases and questions that express degrees of awareness or understanding about a situation or subject

No Comments

No Known Activations