INDEX

Explanations

numerical formats and calculations related to timestamps and dates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ussian

-0.17

jin

-0.17

Ã¦k

-0.16

ÑĪÐºÐ°

-0.15

ousse

-0.15

_ENUM

-0.15

ifton

-0.15

anova

-0.14

Ø·Ø§ÙĦ

-0.14

mith

-0.14

POSITIVE LOGITS

eras

0.15

Led

0.14

pie

0.14

 frank

0.14

xu

0.14

ancia

0.14

bare

0.14

æ¬ł

0.14

wise

0.13

Led

0.13

Activations Density 0.072%

numerical formats and calculations related to timestamps and dates

No Comments

No Known Activations