INDEX

Explanations

terms related to public initiatives and collaborative efforts

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

agate

-0.15

ittel

-0.14

/Internal

-0.14

Dispose

-0.14

ŀæĢ§

-0.14

MeasureSpec

-0.14

CESS

-0.13

 incumb

-0.13

gross

-0.13

@param

-0.13

POSITIVE LOGITS

entes

0.17

razier

0.15

ubi

0.15

alla

0.15

jet

0.15

aru

0.14

rant

0.14

Lis

0.14

bach

0.14

Ð²Ð¸Ð¹

0.14

Activations Density 0.495%

terms related to public initiatives and collaborative efforts

No Comments

No Known Activations