INDEX

Explanations

words that emphasize totality or completeness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

iest

-0.18

eyse

-0.16

 pron

-0.15

ulan

-0.15

stoup

-0.14

light

-0.14

pered

-0.14

 total

-0.14

ãģĦãģ¦

-0.14

Ø±Ø§ÙĨÛĮ

-0.14

POSITIVE LOGITS

ties

0.29

mente

0.20

ments

0.19

maal

0.17

most

0.16

LY

0.16

/part

0.15

idades

0.15

losure

0.15

lice

0.14

Activations Density 0.017%

words that emphasize totality or completeness

No Comments

No Known Activations