INDEX

Explanations

phrases related to social interactions or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

isz

-0.15

zv

-0.15

 Downing

-0.15

usto

-0.15

å¿Ĺ

-0.14

esso

-0.14

 WARRANT

-0.13

iesz

-0.13

coins

-0.13

POSITIVE LOGITS

umas

0.16

à¤ľà¤°

0.16

ÄĽr

0.15

Ð»Ð¾Ñĩ

0.15

Å¡ak

0.15

#aa

0.14

odyn

0.14

ensi

0.14

ephy

0.14

ì²

0.14

Activations Density 0.166%

phrases related to social interactions or events

No Comments

No Known Activations