INDEX

Explanations

references to the concept of "world," particularly in relation to significance or prominence in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

imate

-0.15

 tick

-0.15

`\

-0.15

 Tick

-0.14

appers

-0.14

mdb

-0.14

emer

-0.14

emale

-0.14

 autos

-0.14

 then

-0.14

POSITIVE LOGITS

.scalablytyped

0.22

ÎµÏĦ

0.17

Tro

0.15

'gc

0.14

tone

0.14

 moÅ¼

0.14

ãĥ¼ãĥª

0.13

irsch

0.13

NAL

0.13

ÃĹ↵↵

0.13

Activations Density 0.017%

references to the concept of "world," particularly in relation to significance or prominence in context

No Comments

No Known Activations