INDEX

Explanations

references to governmental or official actions and positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ipo

-0.14

okus

-0.14

Ã§

-0.14

ifest

-0.13

sis

-0.13

eleri

-0.13

itud

-0.13

ds

-0.13

ahoma

-0.13

bero

-0.13

POSITIVE LOGITS

 move

0.33

 moves

0.24

move

0.23

 spokesman

0.22

 statement

0.22

 spokeswoman

0.21

Move

0.20

 spokesperson

0.20

-move

0.20

 exact

0.20

Activations Density 0.164%

references to governmental or official actions and positions

No Comments

No Known Activations