INDEX

Explanations

mentions of the word "knight."

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

éĩı

-0.16

nist

-0.16

.EventQueue

-0.15

.AutoScaleMode

-0.15

eko

-0.15

hop

-0.15

DonaldTrump

-0.15

rait

-0.14

/gtest

-0.14

HeaderCode

-0.14

POSITIVE LOGITS

esi

0.15

awi

0.15

oodoo

0.14

-toggle

0.14

 sola

0.14

æīĢ

0.14

andes

0.14

ed

0.13

avir

0.13

Activations Density 0.004%

mentions of the word "knight."

No Comments

No Known Activations