INDEX

Explanations

references to specific locations 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 @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

acos

-0.16

Ã´m

-0.15

 Spirits

-0.15

Bounding

-0.14

adla

-0.14

éħ

-0.14

æĶ»

-0.14

áº£

-0.14

rava

-0.14

oppers

-0.14

POSITIVE LOGITS

who

0.18

who

0.16

are

0.15

 olan

0.15

0.14

qui

0.14

vice

0.14

ÙħØ§ÙĨÛĮ

0.14

osphere

0.13

Activations Density 0.134%

references to specific locations and organizations

No Comments

No Known Activations