INDEX

Explanations

the word "in" indicating locations or contexts within a text

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

ulum

-0.15

ÌĪ

-0.15

ara

-0.15

McG

-0.15

templ

-0.14

elp

-0.14

Ð´ÐµÐ»

-0.14

 verk

-0.14

 Ð¿ÐµÑĢÐµÐ³

-0.14

 Traverse

-0.13

POSITIVE LOGITS

 Schneider

0.15

vens

0.15

*scale

0.14

chy

0.14

sil

0.14

chyb

0.14

endregion

0.14

uplicated

0.14

.toFloat

0.13

conde

0.13

Activations Density 0.036%

the word "in" indicating locations or contexts within a text

No Comments

No Known Activations