INDEX

Explanations

references to Java and Apache libraries and frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

is

-0.17

rane

-0.15

lej

-0.15

ien

-0.14

$__

-0.14

anus

-0.14

urm

-0.14

ulus

-0.14

Ã¼le

-0.14

nestjs

-0.13

POSITIVE LOGITS

LOSE

0.15

IGH

0.15

achte

0.14

 Hast

0.14

ISON

0.14

Ø±Ùĥ

0.13

hoff

0.13

velt

0.13

-grey

0.13

ripp

0.12

Activations Density 0.027%

references to Java and Apache libraries and frameworks

No Comments

No Known Activations