INDEX

Explanations

time-related phrases

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

 Hood

-0.15

 Shannon

-0.15

urus

-0.15

ÑĪÐµÐ»

-0.15

usercontent

-0.14

uhl

-0.14

uffman

-0.14

fro

-0.13

sk

-0.13

POSITIVE LOGITS

azi

0.20

ubat

0.19

ormsg

0.18

oca

0.16

aders

0.16

 Tort

0.16

 tort

0.15

zac

0.15

eyJ

0.15

pent

0.15

Activations Density 0.019%

time-related phrases

No Comments

No Known Activations