INDEX

Explanations

terms related to award nominations and honors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

pery

-0.19

Sky

-0.16

Sky

-0.16

anness

-0.16

hurst

-0.15

 stake

-0.15

ict

-0.15

ëĪ

-0.15

quartered

-0.14

ock

-0.14

POSITIVE LOGITS

erty

0.17

 eiusmod

0.17

ittle

0.17

zens

0.16

ument

0.16

urnal

0.16

zych

0.16

ulong

0.15

uments

0.15

ASN

0.15

Activations Density 0.050%

terms related to award nominations and honors

No Comments

No Known Activations