INDEX

Explanations

proper nouns, particularly names and organizations

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

ObjectContext

-0.16

oldem

-0.16

íĭ

-0.15

å§Ķ

-0.15

çĲ³

-0.15

ocup

-0.15

iente

-0.14

earned

-0.14

oppel

-0.14

lico

-0.13

POSITIVE LOGITS

DRV

0.17

ÑĢÐ°ÑĤ

0.15

Lam

0.15

/py

0.15

 sing

0.14

ç¬¦

0.14

wap

0.14

lam

0.14

criptor

0.14

aggio

0.13

Activations Density 0.012%

proper nouns, particularly names and organizations

No Comments

No Known Activations