INDEX

Explanations

references to independence and governance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

zimmer

-0.18

odia

-0.17

dap

-0.16

 stunt

-0.14

 Demir

-0.14

itchen

-0.14

ãģĭãģĹ

-0.14

portlet

-0.14

adele

-0.13

istros

-0.13

POSITIVE LOGITS

Rol

0.16

egl

0.16

 blind

0.15

 Farr

0.15

 Earl

0.15

 independence

0.15

irth

0.15

_shared

0.14

 offsetX

0.14

Activations Density 0.152%

references to independence and governance

No Comments

No Known Activations