INDEX

Explanations

prominent figures and their affiliations within an organization or event

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

Negative Logits

ponent

-0.16

_solve

-0.15

chg

-0.15

otr

-0.14

ASI

-0.14

íķĢ

-0.14

Vit

-0.13

eref

-0.13

isl

-0.13

aleur

-0.13

POSITIVE LOGITS

elts

0.14

urf

0.14

 Verg

0.14

Ø¨Ø¯

0.14

ibase

0.13

Î´Î¬

0.13

.calls

0.13

à¸ģà¸£

0.13

NV

0.13

ÑģÑĤÑĢ

0.13

Activations Density 0.203%

prominent figures and their affiliations within an organization or event

No Known Activations