INDEX

Explanations

instances of the word "last" and its variations, indicating a focus on recency or temporal relevance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 Years

-0.19

Years

-0.19

Enumerator

-0.17

 YEARS

-0.16

years

-0.16

YS

-0.15

 YÄ±l

-0.15

ÑĢÑĥÐ±

-0.15

oom

-0.15

orns

-0.15

POSITIVE LOGITS

 month

0.31

 week

0.31

month

0.21

-month

0.20

week

0.18

 Month

0.18

 weekend

0.18

Month

0.18

-week

0.18

urtle

0.17

Activations Density 0.032%

instances of the word "last" and its variations, indicating a focus on recency or temporal relevance

No Comments

No Known Activations