INDEX

Explanations

references to academic experiences and institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

uce

-0.16

iteur

-0.15

 elev

-0.15

nore

-0.14

ouce

-0.14

atto

-0.14

hci

-0.14

_minus

-0.14

ICA

-0.14

iveau

-0.14

POSITIVE LOGITS

XHR

0.15

 Partial

0.15

 topl

0.14

ÏĦÏĤ

0.14

 spread

0.14

à¸£à¸§

0.14

ropy

0.14

 RequestMethod

0.13

~(

0.13

getCell

0.13

Activations Density 0.262%

references to academic experiences and institutions

No Comments

No Known Activations