INDEX

Explanations

references to items or subjects being mentioned repeatedly within a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

fillType

-0.16

 itself

-0.16

MR

-0.16

erif

-0.16

ivals

-0.14

ware

-0.14

ãĥ¼ãĥ«

-0.14

ÐµÐ´Ð¶

-0.14

Ã¡

-0.14

POSITIVE LOGITS

 yourselves

0.15

ãĥ³ãĤ¯

0.15

imbus

0.15

asal

0.14

ira

0.14

 Yourself

0.14

æĨ

0.14

.foundation

0.14

ÃŃr

0.14

ieme

0.14

Activations Density 0.167%

references to items or subjects being mentioned repeatedly within a context

No Comments

No Known Activations