INDEX

Explanations

references to the word "magic" 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 @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

aklÄ±

-0.18

 insp

-0.17

umph

-0.17

issance

-0.17

orial

-0.16

phinx

-0.15

 Gazette

-0.15

pty

-0.15

Ð¶Ð½Ð¾

-0.15

ÃĶ

-0.14

POSITIVE LOGITS

pac

0.14

æĶ

0.14

owski

0.14

èŃ

0.14

 Ming

0.13

nut

0.13

 Buckingham

0.13

foot

0.13

uper

0.13

Activations Density 0.006%

references to the word "magic" in various contexts

No Comments

No Known Activations