INDEX

Explanations

references to organizations and entities, particularly in an educational or activist context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

Fixture

-0.15

 recovering

-0.14

-controls

-0.14

iaux

-0.14

panied

-0.13

elin

-0.13

ecial

-0.13

 Supports

-0.13

 supports

-0.13

åħĪ

-0.13

POSITIVE LOGITS

 nevertheless

0.25

 nonetheless

0.22

 find

0.19

 wasted

0.19

find

0.18

 finds

0.18

 suddenly

0.18

 looks

0.18

now

0.18

 finally

0.17

Activations Density 0.199%

references to organizations and entities, particularly in an educational or activist context

No Comments

No Known Activations