INDEX

Explanations

references to specific locations 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 @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

anol

-0.16

eyn

-0.15

amo

-0.15

antro

-0.15

è¢ĭ

-0.14

oda

-0.14

inci

-0.14

Ð°Ð»Ñİ

-0.14

amer

-0.14

Î¼Î¬

-0.14

POSITIVE LOGITS

usi

0.16

ech

0.15

.nih

0.15

 Bliss

0.14

 Leadership

0.14

Lid

0.14

urate

0.14

KeyEvent

0.13

 Domin

0.13

 fore

0.13

Activations Density 0.351%

references to specific locations and names

No Comments

No Known Activations