INDEX

Explanations

numerical data points or statistics related to events and people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

 Priv

-0.18

 priv

-0.17

ullo

-0.17

Priv

-0.15

ovatel

-0.15

/includes

-0.15

 Bond

-0.15

rome

-0.15

ieber

-0.15

inalg

-0.14

POSITIVE LOGITS

tega

0.17

Ø¹Ø§

0.15

 Alto

0.15

 è¶ħ

0.15

MBER

0.14

 Soccer

0.14

onec

0.14

MR

0.14

_dual

0.14

SUM

0.14

Activations Density 0.200%

numerical data points or statistics related to events and people

No Comments

No Known Activations