INDEX

Explanations

words indicating large quantities or frequencies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

iggs

-0.16

si

-0.16

editary

-0.16

à¥įà¤·à¤£

-0.15

 certain

-0.15

elden

-0.15

IENCE

-0.15

ØªÙĬÙĨ

-0.14

inem

-0.14

ÙĩØ§ÛĮ

-0.14

POSITIVE LOGITS

 amounts

0.24

amount

0.24

 amount

0.22

 sclerosis

0.21

 Amount

0.19

 number

0.19

Amount

0.18

 times

0.18

 sayÄ±da

0.17

 ways

0.17

Activations Density 0.034%

words indicating large quantities or frequencies

No Comments

No Known Activations