INDEX

Explanations

references to planning, timing, and decision-making in relation to events and expectations

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

iaÅĤa

-0.15

andal

-0.15

à¹Īà¸²à¸¢

-0.15

 Ð¾Ð±Ð¾ÑĢ

-0.14

ucceeded

-0.14

 pathname

-0.14

Played

-0.14

Received

-0.14

erif

-0.14

Generated

-0.13

POSITIVE LOGITS

 planned

0.44

 fore

0.38

 originally

0.38

 expected

0.37

 intended

0.35

 forecast

0.35

 promised

0.35

 anticipated

0.34

 predicted

0.33

 desired

0.32

Activations Density 0.345%

references to planning, timing, and decision-making in relation to events and expectations

No Comments

No Known Activations