INDEX

Explanations

expressions of uncertainty or questioning related to personal experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

iasi

-0.15

ãĤµãĤ¤

-0.15

Ð½Ð¸ÑĨÑĸ

-0.14

ehr

-0.14

ilyn

-0.14

IntArray

-0.13

uste

-0.13

à¥įà¤°à¤¸

-0.13

ê°ķ

-0.13

TestingModule

-0.13

POSITIVE LOGITS

 maybe

0.20

 possibly

0.19

maybe

0.18

 certainly

0.16

 possibility

0.16

Or

0.16

possibly

0.16

 hypothesis

0.15

complexContent

0.15

 Maybe

0.14

Activations Density 0.335%

expressions of uncertainty or questioning related to personal experiences

No Comments

No Known Activations