INDEX

Explanations

references to placeholder pages for specific individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ousel

-0.16

rang

-0.15

\application

-0.15

ìĬ¹

-0.15

ONTAL

-0.15

ingroup

-0.14

Ã¦kke

-0.14

PropertyChanged

-0.14

 gerne

-0.14

IODevice

-0.14

POSITIVE LOGITS

0.19

Pac

0.17

ob

0.16

PAC

0.15

 class

0.15

 Still

0.15

hone

0.15

ana

0.15

Activations Density 0.007%

references to placeholder pages for specific individuals

No Comments

No Known Activations