INDEX

Explanations

instances of the word "go" and its variations in different phrases and contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

outu

-0.18

amburger

-0.16

 licence

-0.15

Ð¾Ð²Ð°ÑĢ

-0.15

Ø±Ø¯

-0.14

æ²»

-0.14

Ð¾Ð´Ñĥ

-0.14

acht

-0.14

Ð°ÐºÐ¸

-0.14

aturity

-0.13

POSITIVE LOGITS

Ø³ØªÛĮ

0.16

owi

0.15

azed

0.15

odesk

0.15

 dere

0.15

-ahead

0.15

AGMA

0.15

iyet

0.14

SSIP

0.14

 Cloth

0.14

Activations Density 0.055%

instances of the word "go" and its variations in different phrases and contexts

No Comments

No Known Activations