INDEX

Explanations

instances of quantities, capacities, and limitations in various contexts

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

ç»ĻæĪĳ

-0.17

eux

-0.16

è®©æĪĳ

-0.16

æĺ¯æĪĳ

-0.16

yla

-0.14

orne

-0.14

 hatta

-0.13

ank

-0.13

ï¼ĮçĦ¶åĲİ

-0.13

him

-0.13

POSITIVE LOGITS

 there

0.39

it

0.29

there

0.27

 ÙģØ¥ÙĨ

0.26

 they

0.25

 nobody

0.25

we

0.24

 everything

0.23

 thÃ¬

0.23

 nothing

0.22

Activations Density 1.042%

instances of quantities, capacities, and limitations in various contexts

No Comments

No Known Activations