INDEX

Explanations

terms related to educational programs and systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

esz

-0.15

nun

-0.15

onyms

-0.14

LM

-0.14

orsche

-0.14

aupt

-0.14

usz

-0.13

udios

-0.13

POSITIVE LOGITS

äººåĵ¡

0.15

 hÆ¡i

0.14

ieg

0.14

çĢ

0.14

imoto

0.14

coli

0.14

/ts

0.13

Ð»Ð¾ÑģÑĮ

0.13

UnderTest

0.13

onian

0.13

Activations Density 0.050%

terms related to educational programs and systems

No Comments

No Known Activations