INDEX

Explanations

references to vocational roles and professional classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

anka

-0.17

ump

-0.15

ilde

-0.15

·

-0.15

junction

-0.14

ori

-0.14

enberg

-0.14

æĭħå½ĵ

-0.14

Dry

-0.14

áº£y

-0.13

POSITIVE LOGITS

ekli

0.16

 omas

0.14

 Glob

0.14

 Globals

0.14

idel

0.14

ekim

0.14

alink

0.14

imd

0.14

 Leban

0.14

Activations Density 0.361%

references to vocational roles and professional classifications

No Comments

No Known Activations