INDEX

Explanations

instances of the word "grew" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

iden

-0.17

à¸Ńà¸Ķ

-0.15

.av

-0.15

emez

-0.15

nez

-0.15

McL

-0.15

/off

-0.15

fort

-0.15

PIO

-0.14

 Brew

-0.14

POSITIVE LOGITS

 growing

0.42

 Growing

0.38

 grow

0.38

 grew

0.36

 grows

0.35

Growing

0.35

Grow

0.33

-growing

0.32

grow

0.30

-grow

0.30

Activations Density 0.007%

instances of the word "grew" and its variations

No Comments

No Known Activations

instances of the word "grew" and its variations

No Comments

No Known Activations