INDEX

Explanations

phrases indicating authority or positioning within institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

erie

-0.18

ÅĽcie

-0.17

strar

-0.16

Å¡t

-0.16

tas

-0.16

gado

-0.16

lich

-0.16

erer

-0.16

eÅŁ

-0.16

eration

-0.16

POSITIVE LOGITS

 least

0.23

tribution

0.20

lassian

0.19

ollen

0.18

least

0.17

OMIC

0.17

tele

0.16

olls

0.16

elier

0.16

ioxid

0.15

Activations Density 0.096%

phrases indicating authority or positioning within institutions

No Comments

No Known Activations

phrases indicating authority or positioning within institutions

No Comments

No Known Activations