INDEX

Explanations

proper nouns and names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ndon

-0.18

ibur

-0.18

sw

-0.16

atoria

-0.15

 diss

-0.15

ampions

-0.15

ushi

-0.14

á»Ļc

-0.14

prech

-0.14

enda

-0.14

POSITIVE LOGITS

Tr

0.24

.Tr

0.17

Tr

0.16

-Tr

0.16

 Bedford

0.16

uras

0.14

 nghiá»ĩm

0.14

(TR

0.14

(tr

0.14

.TR

0.14

Activations Density 0.047%

proper nouns and names

No Comments

No Known Activations