INDEX

Explanations

markers of affirmative and negative statements in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

zap

-0.18

hydrate

-0.17

oba

-0.15

ìĹ¼

-0.15

ewis

-0.15

ivan

-0.14

usa

-0.14

daughter

-0.14

zes

-0.14

ills

-0.14

POSITIVE LOGITS

 promised

0.23

 promise

0.23

 promises

0.20

 Promise

0.19

Promise

0.17

agi

0.15

 meant

0.15

ullah

0.15

promise

0.14

 Sounds

0.14

Activations Density 0.002%

markers of affirmative and negative statements in various contexts

No Comments

No Known Activations