INDEX

Explanations

character sequences or patterns typically associated with specific names or terminology

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

mers

-0.18

oon

-0.17

cts

-0.16

mayan

-0.15

Extend

-0.14

meet

-0.14

tsky

-0.14

emi

-0.14

ÅĤ

-0.14

ente

-0.14

POSITIVE LOGITS

ernaut

0.17

_attached

0.15

redits

0.15

((__

0.14

Ã³a

0.14

Wa

0.14

Ø§ÙĪÙĩ

0.14

 invent

0.14

ÐµÐ³Ð¾ÑĢ

0.14

ceed

0.13

Activations Density 0.053%

character sequences or patterns typically associated with specific names or terminology

No Comments

No Known Activations