INDEX

Explanations

references to organizations or centers related to various fields or initiatives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ument

-0.19

arten

-0.16

andle

-0.16

ogan

-0.16

anz

-0.15

oline

-0.15

-speaking

-0.15

kÃ¼

-0.14

ogg

-0.14

FromClass

-0.14

POSITIVE LOGITS

lify

0.18

pieces

0.18

0.17

0.16

pulse

0.15

Glyph

0.15

polate

0.15

 ages

0.15

 Gravity

0.15

 gravity

0.14

Activations Density 0.066%

references to organizations or centers related to various fields or initiatives

No Comments

No Known Activations