INDEX

Explanations

repeated phrases or common elements in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

odv

-0.15

own

-0.14

ocs

-0.14

StandardItem

-0.14

ints

-0.14

inke

-0.14

eter

-0.14

 defaultMessage

-0.13

omy

-0.13

porate

-0.13

POSITIVE LOGITS

//{{

0.15

cke

0.14

Ì

0.14

/embed

0.14

ardu

0.14

ãĥ¼ãĤ¹

0.14

 GÃ¼n

0.13

Pu

0.13

_iso

0.13

ëĭ¤ê°Ģ

0.13

Activations Density 0.004%

repeated phrases or common elements in various contexts

No Comments

No Known Activations