INDEX

Explanations

occurrences of the word "innovate" and its variations, indicating a focus on innovation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ÙĤÙĦ

-0.17

erais

-0.17

ebb

-0.16

ificio

-0.16

bags

-0.16

untas

-0.16

assic

-0.16

empor

-0.15

aterno

-0.15

entina

-0.15

POSITIVE LOGITS

ative

0.31

ativ

0.21

ATIVE

0.20

ISION

0.19

ate

0.19

ators

0.19

ations

0.18

ator

0.18

alue

0.18

ision

0.18

Activations Density 0.003%

occurrences of the word "innovate" and its variations, indicating a focus on innovation

No Comments

No Known Activations