INDEX

Explanations

directional words indicating movement or orientation

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

usc

-0.17

ieber

-0.15

senal

-0.14

ÙĪÙĦÙĬ

-0.14

emachine

-0.14

oten

-0.14

æĪ¶

-0.14

mary

-0.13

uco

-0.13

azzi

-0.13

POSITIVE LOGITS

acades

0.18

Bay

0.16

roup

0.15

leigh

0.15

/inet

0.15

ap

0.15

arya

0.15

tra

0.15

wax

0.15

Bay

0.14

Activations Density 0.003%

directional words indicating movement or orientation

No Comments

No Known Activations