INDEX

Explanations

names related to leadership and responsibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

iple

-0.16

 Petit

-0.15

 Highland

-0.15

usc

-0.14

 Allan

-0.14

 Turk

-0.14

Ã¢n

-0.14

½

-0.14

ika

-0.13

à¸±à¸ģ

-0.13

POSITIVE LOGITS

erosis

0.18

ceae

0.18

anooga

0.17

okedex

0.17

ccione

0.16

swick

0.16

rrha

0.16

/filepath

0.16

_kses

0.15

('@/

0.15

Activations Density 0.055%

names related to leadership and responsibility

No Comments

No Known Activations