INDEX

Explanations

numerical data or identifiers associated with events or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

etwork

-0.16

ionage

-0.15

eryl

-0.15

 incapac

-0.14

iculo

-0.14

pressor

-0.14

 hookers

-0.14

pok

-0.14

unga

-0.14

ych

-0.14

POSITIVE LOGITS

(#)

0.16

hyp

0.15

lington

0.15

PLL

0.14

agher

0.14

dcc

0.14

 multiples

0.14

 minerals

0.14

 Sphere

0.14

esin

0.13

Activations Density 0.005%

numerical data or identifiers associated with events or entities

No Comments

No Known Activations