INDEX

Explanations

elements related to figures and graphical representations in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

EC

-0.16

agna

-0.16

loquent

-0.15

::__

-0.15

à¸²à¸ĩ

-0.14

istra

-0.14

(AF

-0.14

bj

-0.14

readcr

-0.14

ToMany

-0.14

POSITIVE LOGITS

egend

0.15

 gratuites

0.15

 pÃ¡s

0.14

ipa

0.14

cob

0.13

á»Ĩ

0.13

 Regel

0.13

chg

0.13

LETTE

0.13

/Instruction

0.13

Activations Density 0.020%

elements related to figures and graphical representations in a document

No Comments

No Known Activations