INDEX

Explanations

references to the speaker or writer's personal experiences and opinions

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

ught

-0.17

abouts

-0.16

burgh

-0.16

æľ«

-0.16

.fm

-0.16

avenport

-0.16

eno

-0.14

UGHT

-0.14

å´

-0.14

Î¼Î®

-0.14

POSITIVE LOGITS

DEX

0.16

sth

0.15

ronic

0.15

Spy

0.15

edere

0.14

ryn

0.14

 consent

0.14

 mage

0.14

elts

0.14

Activations Density 0.182%

references to the speaker or writer's personal experiences and opinions

No Comments

No Known Activations