INDEX

Explanations

references to ownership or individuality

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

á»¥c

-0.15

lok

-0.14

HRESULT

-0.14

 åĶ

-0.14

odie

-0.14

boo

-0.14

lip

-0.14

SEA

-0.14

 defaultstate

-0.14

POSITIVE LOGITS

anga

0.18

ervo

0.18

0.17

ickerView

0.15

ypy

0.15

itÃł

0.15

afka

0.14

tery

0.14

age

0.14

PEC

0.14

Activations Density 0.029%

references to ownership or individuality

No Comments

No Known Activations