INDEX

Explanations

sequences of numbers or patterns that are relevant to data analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ickers

-0.17

ãģĭãģĦ

-0.15

holm

-0.15

forth

-0.15

Submitted

-0.14

_PLUS

-0.14

_ASCII

-0.14

bol

-0.14

íħ

-0.14

ÃŃl

-0.14

POSITIVE LOGITS

SizeMode

0.19

ths

0.16

pect

0.15

Lay

0.14

 Healthcare

0.14

LOC

0.14

 Twig

0.14

-ajax

0.14

estic

0.13

 Sandra

0.13

Activations Density 0.130%

sequences of numbers or patterns that are relevant to data analysis

No Comments

No Known Activations