INDEX

Explanations

references to the Star Wars franchise

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

Matchers

-0.17

ivor

-0.15

yal

-0.15

imat

-0.14

Indexes

-0.14

rescia

-0.14

imas

-0.14

 nguyá»ĩn

-0.14

 Freedom

-0.14

bable

-0.14

POSITIVE LOGITS

icker

0.15

ÏĢÎ·

0.15

agara

0.15

uby

0.14

SSIP

0.14

 until

0.14

RU

0.13

 till

0.13

-normal

0.13

Activations Density 0.004%

references to the Star Wars franchise

No Comments

No Known Activations