INDEX

Explanations

expressions related to performance and acting experiences

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

å¤ªéĥİ

-0.15

erland

-0.15

lena

-0.15

âĳł

-0.15

tero

-0.15

app

-0.15

atra

-0.14

reff

-0.14

urette

-0.13

 blessed

-0.13

POSITIVE LOGITS

ÏĦÎ¹ÎºÎ±

0.15

ObjectContext

0.14

 Jaune

0.14

kaÃ§

0.14

 Gregory

0.14

enti

0.13

acÃŃ

0.13

LOPT

0.13

anean

0.13

LastError

0.13

Activations Density 0.023%

expressions related to performance and acting experiences

No Known Activations