INDEX

Explanations

proper nouns related to institutions or notable places

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

unt

-0.17

unts

-0.14

izard

-0.14

izards

-0.14

 crash

-0.14

abad

-0.14

emoc

-0.13

 mean

-0.13

unt

-0.13

itis

-0.13

POSITIVE LOGITS

velte

0.16

Î³Î¿Ïħ

0.15

ÑĹÐ²

0.15

SizePolicy

0.14

/Core

0.14

lap

0.14

UPPORTED

0.14

 getenv

0.14

ynes

0.14

Ä±ndÄ±r

0.14

Activations Density 0.136%

proper nouns related to institutions or notable places

No Comments

No Known Activations