INDEX

Explanations

references to various types of systems, programs, and structured entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ngo

-0.17

eck

-0.16

usch

-0.15

 Cord

-0.15

arda

-0.15

-0.14

ÑģÑı

-0.14

 Vern

-0.14

erta

-0.14

POSITIVE LOGITS

inde

0.16

 indeed

0.16

overall

0.15

UnderTest

0.15

andle

0.15

Ð¾Ð»Ð¾Ð´

0.15

éĩİ

0.14

ãĤ¶ãĥ¼

0.14

athan

0.14

&a

0.14

Activations Density 0.177%

references to various types of systems, programs, and structured entities

No Comments

No Known Activations