INDEX

Explanations

references to common connections or shared experiences among individuals or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lier

-0.17

uars

-0.16

 Crush

-0.15

oce

-0.15

rze

-0.14

ÑĢÐ¸ÑģÑĤ

-0.14

 stereotype

-0.14

aleb

-0.13

Ã¶rt

-0.13

 Honest

-0.13

POSITIVE LOGITS

 shared

0.20

/shared

0.20

(shared

0.18

åħ±

0.18

_shared

0.17

ÐµÐ´Ð¸

0.17

ertz

0.16

shared

0.16

 åħ±

0.16

 common

0.15

Activations Density 0.234%

references to common connections or shared experiences among individuals or groups

No Comments

No Known Activations