INDEX

Explanations

phrases related to calls to action or invitations to engage with content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

Äįku

-0.15

antino

-0.14

apolis

-0.14

 noci

-0.14

ÐºÐµÑĤ

-0.14

ocu

-0.14

unprocessable

-0.14

Ð°Ð½ÑĸÑı

-0.14

odo

-0.13

Trademark

-0.13

POSITIVE LOGITS

ixin

0.15

stein

0.15

 Barg

0.15

 Baba

0.14

atta

0.14

REP

0.14

_GB

0.14

 Coupons

0.14

iani

0.14

isel

0.14

Activations Density 0.009%

phrases related to calls to action or invitations to engage with content

No Comments

No Known Activations