INDEX

Explanations

entities and names associated with legal or official 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

ycop

-0.15

logen

-0.15

 lesbi

-0.15

 Aviv

-0.15

omanip

-0.15

memcpy

-0.15

_DEFINE

-0.14

lep

-0.14

fte

-0.14

Ãĺ

-0.14

POSITIVE LOGITS

 Whitney

0.19

baugh

0.17

 Maver

0.17

Og

0.17

 Bracket

0.16

Fah

0.16

 Voor

0.15

illard

0.15

 Chase

0.15

odate

0.15

Activations Density 0.185%

entities and names associated with legal or official contexts

No Comments

No Known Activations