INDEX

Explanations

references to social interactions and exchanges

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

 ÑĢÐµÐ²

-0.15

Ð¶Ñĥ

-0.14

 eldre

-0.14

chan

-0.13

oman

-0.13

 mutable

-0.13

 slowed

-0.13

 altern

-0.13

 slows

-0.13

POSITIVE LOGITS

 depart

0.38

 departure

0.35

 leave

0.33

 Depart

0.33

 exit

0.32

 leaving

0.30

Depart

0.30

ç¦»å¼Ģ

0.29

depart

0.29

 departed

0.29

Activations Density 0.483%

references to social interactions and exchanges

No Comments

No Known Activations