INDEX

Explanations

phrases related to user interactions and requests, particularly for reporting, submitting, and appointing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

urum

-0.17

ometr

-0.15

jes

-0.15

nock

-0.15

Ø³ØªØ§ÙĨ

-0.14

anager

-0.14

leans

-0.14

eydi

-0.14

Ð¸ÑģÐ»Ð¾Ð²

-0.14

hack

-0.14

POSITIVE LOGITS

á»ĳt

0.16

SPATH

0.15

RB

0.14

MODE

0.14

oth

0.14

_MAXIMUM

0.14

ajor

0.14

è«

0.13

IntArray

0.13

 Tobias

0.13

Activations Density 0.420%

phrases related to user interactions and requests, particularly for reporting, submitting, and appointing

No Comments

No Known Activations