INDEX

Explanations

strong affirmative statements and certainty in opinions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 realmente

-0.19

 really

-0.15

pac

-0.15

ificio

-0.15

 vraiment

-0.15

really

-0.15

à¹ģà¸Ĺ

-0.14

æł¹æľ¬

-0.14

 actually

-0.14

 Ð²Ð¾Ð¾Ð±ÑīÐµ

-0.14

POSITIVE LOGITS

NOT

0.17

/pro

0.15

 worth

0.15

/random

0.14

indr

0.13

ãģªãģĮãĤī

0.13

Za

0.13

oire

0.13

lia

0.13

ahir

0.13

Activations Density 0.055%

strong affirmative statements and certainty in opinions

No Comments

No Known Activations

strong affirmative statements and certainty in opinions

No Comments

No Known Activations