INDEX

Explanations

phrases that indicate frustration or discontent with complex game mechanics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ears

-0.16

Abr

-0.15

 Orig

-0.15

 confinement

-0.15

irie

-0.14

 orig

-0.14

sam

-0.14

ious

-0.14

 recom

-0.13

egin

-0.13

POSITIVE LOGITS

 creep

0.24

Cre

0.21

 Memory

0.18

cre

0.18

/memory

0.17

cre

0.17

Cre

0.17

Memory

0.17

.energy

0.17

 Energy

0.17

Activations Density 0.001%

phrases that indicate frustration or discontent with complex game mechanics

No Comments

No Known Activations