INDEX

Explanations

statements expressing uncertainty or concern about various issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

posta

-0.16

amilia

-0.15

ÙĦÙĦ

-0.14

asInstanceOf

-0.14

isse

-0.14

ordes

-0.13

 happ

-0.13

 getattr

-0.13

 Observatory

-0.13

-dot

-0.12

POSITIVE LOGITS

 growing

0.34

 strong

0.25

-growing

0.24

 increasing

0.23

 little

0.23

 broad

0.23

 Growing

0.23

Growing

0.22

 mounting

0.22

 consensus

0.21

Activations Density 0.094%

statements expressing uncertainty or concern about various issues

No Comments

No Known Activations