INDEX

Explanations

timestamps and dates in the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

legg

-0.15

umber

-0.15

attery

-0.15

pring

-0.14

empo

-0.14

/gallery

-0.14

atra

-0.14

izi

-0.13

apers

-0.13

lector

-0.13

POSITIVE LOGITS

mans

0.16

_subplot

0.15

rette

0.15

chal

0.14

auf

0.14

OPS

0.14

Qualifier

0.14

Ð²Ð¸ÑĩÐ°Ð¹

0.14

ubbles

0.14

zug

0.13

Activations Density 0.002%

timestamps and dates in the document

No Comments

No Known Activations