INDEX

Explanations

elements related to system functionality and performance issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

avel

-0.14

ipes

-0.14

ohn

-0.14

iÃ³n

-0.14

ruÅ¾

-0.13

ukkan

-0.13

loff

-0.13

ÅĻÃŃÅ¾

-0.13

ocate

-0.13

lyph

-0.13

POSITIVE LOGITS

 working

0.75

 works

0.73

working

0.65

 Works

0.65

 functioning

0.64

 worked

0.63

 Working

0.63

-working

0.62

Working

0.60

 funciona

0.60

Activations Density 0.395%

elements related to system functionality and performance issues

No Comments

No Known Activations

elements related to system functionality and performance issues

No Comments

No Known Activations