INDEX

Explanations

phrases related to decision-making processes and outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 otherwise

-0.18

æīįèĥ½

-0.17

 Otherwise

-0.17

åĲ¦

-0.16

otherwise

-0.15

 OTHERWISE

-0.14

:animated

-0.14

Otherwise

-0.14

ãģĭãģĳ

-0.14

Injected

-0.14

POSITIVE LOGITS

 immediately

0.39

 followed

0.33

 immedi

0.33

 immediate

0.32

 subsequent

0.27

follow

0.27

 subsequently

0.27

 Immediately

0.26

 instantly

0.26

 later

0.26

Activations Density 0.026%

phrases related to decision-making processes and outcomes

No Comments

No Known Activations