INDEX

Explanations

mentions of academic honors and distinctions

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

awa

-0.18

urai

-0.15

voke

-0.15

MBOL

-0.15

ÙĪØ²Ùĩ

-0.14

oot

-0.14

umper

-0.14

arena

-0.14

Doc

-0.14

eli

-0.14

POSITIVE LOGITS

ilig

0.16

hurst

0.15

rale

0.15

à¸±à¹Ī

0.15

 Transcript

0.15

AppBundle

0.14

.liferay

0.14

llib

0.14

ADDE

0.14

erer

0.13

Activations Density 0.006%

mentions of academic honors and distinctions

No Comments

No Known Activations