INDEX

Explanations

specific dates and numerical references in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

arte

-0.16

ovice

-0.15

jed

-0.14

wel

-0.14

ynes

-0.14

andi

-0.14

cg

-0.13

ÏįÏĢ

-0.13

ÑĥÑģÐº

-0.13

utan

-0.13

POSITIVE LOGITS

 Peripheral

0.15

 peripheral

0.15

 FormData

0.15

sink

0.15

atum

0.15

lyph

0.14

 peripherals

0.14

Peripheral

0.14

 Sink

0.14

ramer

0.13

Activations Density 0.049%

specific dates and numerical references in the text

No Comments

No Known Activations