INDEX

Explanations

quantifiers related to quantity or frequency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

-thirds

-0.16

-minute

-0.16

ä¸īå¹´

-0.16

-Ñħ

-0.15

-0.14

rian

-0.14

rado

-0.14

-times

-0.14

 adet

-0.14

ä¸Ģå¹´

-0.14

POSITIVE LOGITS

 many

0.19

 tens

0.17

 erotik

0.16

 ticks

0.16

#__

0.15

 MANY

0.15

lif

0.15

 tent

0.15

dp

0.14

 kred

0.14

Activations Density 0.062%

quantifiers related to quantity or frequency

No Comments

No Known Activations