INDEX

Explanations

concepts related to negative thoughts and positive affirmations

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

civ

-0.17

achen

-0.16

aga

-0.15

iec

-0.15

ima

-0.14

zel

-0.14

bourg

-0.14

lier

-0.14

chn

-0.14

 trope

-0.13

POSITIVE LOGITS

visualization

0.17

 Principle

0.17

 Visualization

0.17

 visualization

0.17

 Ð²Ð½Ñĥ

0.16

 congr

0.16

Attr

0.15

oppel

0.15

 Success

0.15

 Winners

0.15

Activations Density 0.131%

concepts related to negative thoughts and positive affirmations

No Comments

No Known Activations