INDEX

Explanations

pronouns, particularly those related to gender

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

acci

-0.17

agnost

-0.16

ylan

-0.16

utilus

-0.14

lv

-0.13

ritt

-0.13

/of

-0.13

itto

-0.13

redd

-0.13

 cracked

-0.13

POSITIVE LOGITS

AndWait

0.14

Â§Ãĥ

0.14

oriously

0.14

 Vapor

0.13

ÏĥÎºÎµ

0.13

ÑģÑıÐ³

0.13

osc

0.13

Cancelable

0.13

erdem

0.13

Eck

0.13

Activations Density 0.090%

pronouns, particularly those related to gender

No Comments

No Known Activations