INDEX

Explanations

dialogue that involves conflict or threats

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

edl

-0.15

"$

-0.14

chal

-0.13

uien

-0.13

emm

-0.13

otor

-0.13

 character

-0.13

ettel

-0.13

_TestCase

-0.13

"`

-0.12

POSITIVE LOGITS

alian

0.17

0.16

 âĢº

0.14

kre

0.14

êµ°

0.13

ilder

0.13

roma

0.13

fait

0.13

Å¾i

0.12

-Compatible

0.12

Activations Density 0.928%

dialogue that involves conflict or threats

No Comments

No Known Activations