INDEX

Explanations

references to organizations or proper nouns related to entities or individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

eric

-0.18

rak

-0.17

ragon

-0.17

acker

-0.16

aney

-0.16

ÐºÑĥÑĢ

-0.16

raÅ¾

-0.14

ring

-0.14

raya

-0.14

eriod

-0.14

POSITIVE LOGITS

.scalablytyped

0.28

ensen

0.20

ues

0.19

inal

0.18

otten

0.18

uet

0.18

ueil

0.17

enson

0.17

itecture

0.16

Activations Density 0.016%

references to organizations or proper nouns related to entities or individuals

No Comments

No Known Activations