INDEX

Explanations

image credits and references within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ansson

-0.17

æľŃ

-0.17

Ð¾Ð±Ð°

-0.15

adir

-0.14

bearer

-0.14

.getvalue

-0.14

HeaderValue

-0.14

ARA

-0.14

.sourceforge

-0.14

_HEADERS

-0.13

POSITIVE LOGITS

 Britt

0.18

 Brady

0.16

oins

0.14

ftar

0.14

 blush

0.14

à¸´à¸ĩ

0.14

Sci

0.14

upos

0.14

0.13

brick

0.13

Activations Density 0.006%

image credits and references within the text

No Comments

No Known Activations