INDEX

Explanations

proper nouns and names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 grÃ¡tis

-0.16

 Lecture

-0.14

 Display

-0.14

Display

-0.14

agna

-0.14

¢ħ

-0.14

áº¡

-0.13

eno

-0.13

ä½

-0.13

ightly

-0.13

POSITIVE LOGITS

 reporting

0.16

 reviews

0.15

sat

0.15

Reporting

0.15

 explains

0.15

 examines

0.15

 unde

0.15

tal

0.14

exclusive

0.14

 present

0.14

Activations Density 0.077%

proper nouns and names

No Comments

No Known Activations