INDEX

Explanations

expressions of personal emotions and opinions

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

ly

-0.18

tti

-0.16

-0.15

ousand

-0.14

ls

-0.14

line

-0.14

ctors

-0.14

iversity

-0.14

lu

-0.14

lm

-0.13

POSITIVE LOGITS

zelf

0.18

eza

0.16

sop

0.16

-mÃªme

0.14

iá»ĥu

0.14

 Ãĸr

0.14

Äįin

0.13

iag

0.13

ÄĻd

0.13

ylland

0.13

Activations Density 0.222%

expressions of personal emotions and opinions

No Comments

No Known Activations