INDEX

Explanations

references to brands or proprietary names related to products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

instanc

-0.15

angs

-0.14

uck

-0.14

oint

-0.14

umph

-0.14

ets

-0.14

erness

-0.14

raise

-0.14

bare

-0.14

tml

-0.14

POSITIVE LOGITS

0.22

AGON

0.19

adecimal

0.19

xes

0.19

cellent

0.19

odus

0.19

xxxxxxxx

0.18

xx

0.18

xon

0.18

iom

0.18

Activations Density 0.015%

references to brands or proprietary names related to products

No Comments

No Known Activations