INDEX

Explanations

punctuation marks and function calls in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

oupon

-0.15

 Eyes

-0.14

ety

-0.14

ooth

-0.14

Gri

-0.14

ucci

-0.14

 Wrath

-0.14

xon

-0.14

»¿

-0.14

POSITIVE LOGITS

ë²Į

0.17

forma

0.16

ottie

0.15

erset

0.15

reesome

0.15

ruba

0.14

immel

0.14

æľĹ

0.14

cke

0.14

hos

0.14

Activations Density 0.006%

punctuation marks and function calls in code

No Comments

No Known Activations