INDEX

Explanations

questions and expressions of uncertainty regarding truth and integrity in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

orate

-0.15

.toolbox

-0.15

iao

-0.15

amarin

-0.14

enery

-0.14

enga

-0.14

stal

-0.14

erif

-0.14

leston

-0.14

ustin

-0.14

POSITIVE LOGITS

Pon

0.17

AMS

0.15

Gen

0.14

Moy

0.14

 Russ

0.14

elda

0.14

 Lang

0.14

OS

0.13

ans

0.13

nos

0.13

Activations Density 0.514%

questions and expressions of uncertainty regarding truth and integrity in various contexts

No Comments

No Known Activations