INDEX

Explanations

references to specific consulting or research organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ilater

-0.16

-0.15

_WAKE

-0.15

idia

-0.15

åĸ¶

-0.15

ÑĩÐ½Ð¸Ð¹

-0.15

acios

-0.14

ALLE

-0.14

å¯¸

-0.14

Ã©al

-0.14

POSITIVE LOGITS

Tou

0.21

Del

0.21

tou

0.16

del

0.15

 late

0.15

Del

0.15

.touch

0.15

ownik

0.15

vid

0.15

 Late

0.14

Activations Density 0.010%

references to specific consulting or research organizations

No Comments

No Known Activations