INDEX

Explanations

terms related to identification and sourcing information

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

agher

-0.18

agi

-0.17

 addCriterion

-0.17

 voks

-0.15

_dma

-0.14

éļ¾

-0.14

Ã¦k

-0.14

znÃ¡m

-0.14

ushman

-0.14

-alist

-0.14

POSITIVE LOGITS

areas

0.17

 areas

0.17

 potential

0.16

 among

0.16

 exactly

0.15

 Ð¾Ð¿

0.15

 needs

0.15

 whether

0.15

 need

0.15

amber

0.14

Activations Density 0.114%

terms related to identification and sourcing information

No Comments

No Known Activations