INDEX

Explanations

terms associated with administrative or regulatory contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ighton

-0.15

à¹Ħà¸ĭ

-0.15

abei

-0.14

phis

-0.14

æµ©

-0.14

ffe

-0.14

 Priv

-0.14

isz

-0.14

clearfix

-0.13

iw

-0.13

POSITIVE LOGITS

otta

0.15

è£ı

0.15

ë³µ

0.14

'](

0.14

ulas

0.14

 æĦı

0.14

FUL

0.14

uko

0.14

Mayor

0.14

 addCriterion

0.14

Activations Density 0.124%

terms associated with administrative or regulatory contexts

No Comments

No Known Activations