INDEX

Explanations

references to data plotting and axis specifications in scientific or statistical contexts

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

-0.16

Î¯ÏīÎ½

-0.15

ober

-0.15

_kel

-0.15

UBY

-0.15

azzo

-0.14

uentes

-0.14

/utility

-0.14

çģ°

-0.13

POSITIVE LOGITS

 rá»Ŀi

0.16

à¸§à¸¥

0.15

essa

0.15

ailer

0.14

ndon

0.14

oute

0.14

ilig

0.14

iece

0.14

ext

0.13

Ã«n

0.13

Activations Density 0.109%

references to data plotting and axis specifications in scientific or statistical contexts

No Comments

No Known Activations