INDEX

Explanations

mentions of job titles 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 @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 cÃ¡

-0.14

Repository

-0.14

otta

-0.14

 Pattern

-0.14

angu

-0.14

-0.13

acos

-0.13

 pattern

-0.13

phia

-0.13

POSITIVE LOGITS

inesis

0.16

íĹĮ

0.15

usted

0.15

nard

0.14

mh

0.14

ÏģÎ¿Î¹

0.14

orris

0.13

arb

0.13

idable

0.13

 atIndex

0.13

Activations Density 0.050%

mentions of job titles or positions

No Comments

No Known Activations