INDEX

Explanations

conversational phrases and interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

å±Ģ

-0.14

Ã¡ty

-0.14

TestFixture

-0.14

ÑĤÐ°Ð»

-0.13

ureau

-0.13

intl

-0.13

vince

-0.13

ghan

-0.13

apesh

-0.13

.GetBytes

-0.13

POSITIVE LOGITS

VIP

0.15

perhaps

0.14

exam

0.14

 perhaps

0.13

inkle

0.13

 ingresar

0.13

expo

0.13

 bana

0.13

 saliva

0.13

 interviewing

0.13

Activations Density 0.053%

conversational phrases and interactions

No Comments

No Known Activations