INDEX

Explanations

numerical sequences or identifiers in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

antan

-0.19

antal

-0.18

ian

-0.14

adows

-0.14

 ä½ľ

-0.14

owa

-0.13

erap

-0.13

anz

-0.13

antly

-0.13

apel

-0.13

POSITIVE LOGITS

 Licensed

0.16

åħ¹

0.16

/******/

0.14

à¤¾à¤ł

0.14

pong

0.14

è¾°

0.14

Licensed

0.14

ercul

0.14

éĸĵ

0.14

Activations Density 0.002%

numerical sequences or identifiers in various contexts

No Comments

No Known Activations