INDEX

Explanations

front end positions or references in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

anooga

-0.15

ANN

-0.14

agua

-0.14

ziej

-0.14

udev

-0.14

rita

-0.14

thane

-0.13

pone

-0.13

Mim

-0.13

èĮĤ

-0.13

POSITIVE LOGITS

sted

0.17

sold

0.16

yle

0.15

Î¬Î½ÎµÎ¹

0.15

IALIZ

0.14

YLE

0.14

ylim

0.14

amen

0.14

yles

0.14

aran

0.14

Activations Density 0.028%

front end positions or references in various contexts

No Comments

No Known Activations