INDEX

Explanations

names or references to individuals, particularly those of notable significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

Interop

-0.16

stÃŃ

-0.15

smarty

-0.15

Ð²ÐµÑĤ

-0.15

azÄĥ

-0.14

holm

-0.14

achuset

-0.14

udad

-0.14

EPROM

-0.14

atra

-0.14

POSITIVE LOGITS

 John

0.18

_subtype

0.16

 Seed

0.16

 Johnny

0.16

 john

0.15

 JOHN

0.15

John

0.15

 meta

0.14

cle

0.14

Seed

0.14

Activations Density 0.049%

names or references to individuals, particularly those of notable significance

No Comments

No Known Activations