INDEX

Explanations

references to people in positions of authority or organizational leadership

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

FW

-0.14

oload

-0.14

eg

-0.13

Å¯r

-0.13

ãĥ³ãĤ°

-0.13

 Schneider

-0.13

 Â«

-0.13

uthor

-0.13

alet

-0.13

elan

-0.13

POSITIVE LOGITS

GINE

0.13

ìļ°ìĬ¤

0.13

kla

0.13

hots

0.13

dem

0.13

 console

0.12

.less

0.12

 akÄ±l

0.12

 ê²ĥìĿ´ëĭ¤

0.12

EE

0.12

Activations Density 0.089%

references to people in positions of authority or organizational leadership

No Comments

No Known Activations