INDEX

Explanations

references to transgender individuals and issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

burger

-0.18

onso

-0.17

ropa

-0.15

cec

-0.14

eson

-0.14

yr

-0.14

isky

-0.14

intel

-0.14

enha

-0.14

{}.

-0.13

POSITIVE LOGITS

ed

0.18

hardt

0.16

izzy

0.15

obuf

0.14

emic

0.14

ize

0.14

ellt

0.14

 accomplishment

0.14

 norge

0.14

aÃ±a

0.14

Activations Density 0.002%

references to transgender individuals and issues

No Comments

No Known Activations