INDEX

Explanations

mentions of the brand "Pearson."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ijkstra

-0.15

iens

-0.14

odega

-0.14

bu

-0.14

ooth

-0.14

 maybe

-0.14

 along

-0.14

sel

-0.14

POSITIVE LOGITS

pecies

0.17

çĿ

0.17

 cáºŃn

0.16

pid

0.15

æ°ı

0.14

species

0.14

finity

0.14

ÌĨ

0.14

 åĿ

0.13

lev

0.13

Activations Density 0.007%

mentions of the brand "Pearson."

No Comments

No Known Activations