INDEX

Explanations

instances of notable first occurrences or unique events

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

á»ĳt

-0.18

åıĪ

-0.17

ibel

-0.17

ulumi

-0.16

 weiter

-0.16

ATEST

-0.16

æīįèĥ½

-0.16

 Various

-0.15

akan

-0.14

ckt

-0.14

POSITIVE LOGITS

 ever

0.60

 EVER

0.48

-ever

0.45

ever

0.45

 anywhere

0.40

 since

0.35

Ever

0.33

 outside

0.33

 Ever

0.32

EVER

0.30

Activations Density 0.235%

instances of notable first occurrences or unique events

No Comments

No Known Activations