INDEX

Explanations

references to units of time, especially years and decades

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

erah

-0.15

STDOUT

-0.15

oster

-0.14

 incur

-0.14

ÑģÐ°Ð¼

-0.14

 Æ°á»Ľc

-0.14

luet

-0.14

ALA

-0.14

lobber

-0.14

rol

-0.14

POSITIVE LOGITS

 spent

0.45

spent

0.35

 spend

0.28

 away

0.23

 Spend

0.23

 spends

0.23

of

0.20

-long

0.18

 together

0.18

away

0.18

Activations Density 0.112%

references to units of time, especially years and decades

No Comments

No Known Activations