INDEX

Explanations

references to the term "Sedro" associated with specific contexts or inquiries

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

fully

-0.16

fulness

-0.16

ONO

-0.15

 HÃłng

-0.14

ighton

-0.14

eses

-0.14

 elsewhere

-0.14

eron

-0.14

 conting

-0.14

å¾ģ

-0.14

POSITIVE LOGITS

sed

0.26

iments

0.25

Sed

0.24

uced

0.23

uctive

0.22

iment

0.21

uce

0.19

uction

0.18

imentary

0.18

sed

0.18

Activations Density 0.008%

references to the term "Sedro" associated with specific contexts or inquiries

No Comments

No Known Activations