INDEX

Explanations

references to the company Activision

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

enk

-0.17

errorCode

-0.15

AILS

-0.15

ury

-0.15

overy

-0.15

riet

-0.15

comb

-0.15

Ð¶Ðµ

-0.14

alars

-0.14

ÎµÏį

-0.14

POSITIVE LOGITS

ision

0.29

ISION

0.20

 Activ

0.19

 activ

0.17

activ

0.17

ators

0.17

ator

0.17

ating

0.16

cente

0.16

 Directory

0.15

Activations Density 0.010%

references to the company Activision

No Comments

No Known Activations