INDEX

Explanations

phrases expressing skepticism or criticism towards established theories or beliefs

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

 Intermediate

-0.14

coon

-0.14

 Trou

-0.14

ÙĬÙĥ

-0.14

chop

-0.13

inis

-0.13

(æĹ¥

-0.13

à¸µà¸¢à¸£

-0.13

onom

-0.13

TestCase

-0.13

POSITIVE LOGITS

/commons

0.14

innen

0.14

utes

0.14

assi

0.14

UT

0.14

Éµ

0.14

 inertia

0.14

strup

0.14

 Damian

0.14

atham

0.14

Activations Density 0.797%

phrases expressing skepticism or criticism towards established theories or beliefs

No Comments

No Known Activations