INDEX

Explanations

references to individuals' professional backgrounds and achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

rone

-0.15

 CharSet

-0.14

 Drops

-0.14

ongyang

-0.13

rypton

-0.13

chl

-0.13

:normal

-0.13

otel

-0.13

ReadWrite

-0.13

kot

-0.13

POSITIVE LOGITS

 wife

0.17

 natives

0.16

 Previous

0.15

 Prior

0.15

 Wife

0.15

/go

0.15

 Owners

0.15

 rejo

0.15

 enjoys

0.15

 obtaining

0.14

Activations Density 0.144%

references to individuals' professional backgrounds and achievements

No Comments

No Known Activations