INDEX

Explanations

words that denote leadership or refer to top-ranking entities or positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

se

-0.16

ych

-0.15

ment

-0.15

sphere

-0.14

umble

-0.14

Bean

-0.14

maz

-0.14

 environment

-0.14

pie

-0.14

POSITIVE LOGITS

-edge

0.21

Escort

0.18

ãĥ³ãĥĨ

0.16

Ľ°

0.15

áº¥p

0.15

-flight

0.15

strument

0.14

 Escort

0.14

ierge

0.14

irut

0.14

Activations Density 0.010%

words that denote leadership or refer to top-ranking entities or positions

No Comments

No Known Activations