INDEX

Explanations

references to excursions or tour activities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ober

-0.17

uitka

-0.15

aeda

-0.15

idores

-0.14

rolls

-0.14

ulin

-0.14

ethyst

-0.14

ÏĦÎµÎ¯

-0.14

 bore

-0.14

adius

-0.14

POSITIVE LOGITS

osen

0.15

izon

0.15

 khá»ıi

0.14

Ø§Ø¨Ø¹

0.14

abay

0.14

Seb

0.14

iously

0.14

 Dion

0.13

 Ð·Ð°Ð²Ð¾Ð´

0.13

ords

0.13

Activations Density 0.005%

references to excursions or tour activities

No Comments

No Known Activations