INDEX

Explanations

the word "ent" as well as variations and frequencies of the word "of."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

aal

-0.15

tec

-0.14

byn

-0.14

_firestore

-0.14

ìŀ¥

-0.14

ihil

-0.14

Ã¢u

-0.14

Sizes

-0.13

Äĵ

-0.13

 Gian

-0.13

POSITIVE LOGITS

erif

0.17

abee

0.16

anni

0.14

ç´

0.14

 Uncomment

0.14

 Romero

0.14

 EventType

0.14

-With

0.14

 Shelf

0.13

é¡Ķ

0.13

Activations Density 0.024%

the word "ent" as well as variations and frequencies of the word "of."

No Comments

No Known Activations