INDEX

Explanations

references to community engagement in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ymes

-0.19

aba

-0.16

iska

-0.14

isci

-0.14

Ã¼t

-0.14

[of

-0.14

enez

-0.13

<View

-0.13

se

-0.13

POSITIVE LOGITS

 elsewhere

0.40

 nowhere

0.23

 throughout

0.21

 Else

0.20

 anywhere

0.20

 chez

0.20

 wherever

0.20

 everywhere

0.19

else

0.19

Else

0.18

Activations Density 0.347%

references to community engagement in various contexts

No Comments

No Known Activations