INDEX

Explanations

sections of text that include metrics or quantitative information

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

tie

-0.16

theses

-0.14

ervices

-0.14

 ÙģÙĤ

-0.14

rella

-0.14

roi

-0.13

ias

-0.13

á»«

-0.13

iminal

-0.13

sap

-0.13

POSITIVE LOGITS

ÐµÐºÑĤÐ¸

0.16

 è¡

0.15

empor

0.14

 èµ

0.14

.opens

0.14

aira

0.14

0.13

unes

0.13

oad

0.13

strand

0.13

Activations Density 0.079%

sections of text that include metrics or quantitative information

No Comments

No Known Activations