INDEX

Explanations

instances of the letter 'O' in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ostat

-0.16

æĲŃ

-0.15

.Marshal

-0.15

hua

-0.15

ushman

-0.14

bay

-0.14

ometr

-0.14

ÏĦ

-0.14

 Affero

-0.14

artment

-0.14

POSITIVE LOGITS

egan

0.15

.remote

0.15

 Canada

0.15

afs

0.14

ktor

0.14

 McMahon

0.14

 cours

0.14

soc

0.14

IT

0.14

åĨĮ

0.14

Activations Density 0.029%

instances of the letter 'O' in different contexts

No Comments

No Known Activations