INDEX

Explanations

references to fairness and balance in team contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ean

-0.18

prung

-0.14

umpt

-0.14

assi

-0.14

urgeon

-0.14

.RunWith

-0.14

panse

-0.13

anon

-0.13

ATAL

-0.13

 gram

-0.13

POSITIVE LOGITS

adder

0.16

 game

0.15

 playing

0.15

 games

0.15

 play

0.15

 skill

0.14

skill

0.14

-Origin

0.14

 played

0.14

 screenshot

0.14

Activations Density 0.025%

references to fairness and balance in team contexts

No Comments

No Known Activations