INDEX

Explanations

expressions of trust and assurance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

usted

-0.14

sson

-0.14

Nat

-0.14

ksen

-0.14

leton

-0.14

wall

-0.14

.dtd

-0.14

apiro

-0.14

 mens

-0.14

imary

-0.14

POSITIVE LOGITS

ÑĨÐµÐ¿

0.17

ewood

0.16

 desar

0.15

imb

0.14

**/↵↵

0.14

akening

0.14

<Real

0.14

ably

0.14

ewis

0.14

_odd

0.13

Activations Density 0.043%

expressions of trust and assurance

No Comments

No Known Activations