INDEX

Explanations

historical references to specific time periods and significant events

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

ongyang

-0.20

phem

-0.16

ERING

-0.15

ruba

-0.15

inke

-0.15

anki

-0.15

 pager

-0.14

zap

-0.14

uctive

-0.14

ither

-0.14

POSITIVE LOGITS

leur

0.17

forman

0.14

Hol

0.14

_topics

0.14

 pute

0.13

ipay

0.13

ÐµÐºÑĥ

0.13

flip

0.13

 IllegalAccessException

0.13

_Arg

0.13

Activations Density 0.690%

historical references to specific time periods and significant events

No Comments

No Known Activations