INDEX

Explanations

instances of the word "inside" and variations of it in contexts discussing physical or metaphorical spaces

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

eron

-0.19

esters

-0.17

eros

-0.17

ched

-0.17

udi

-0.16

ether

-0.16

lys

-0.16

lo

-0.15

à¸¢à¸Ńà¸Ķ

-0.15

roma

-0.15

POSITIVE LOGITS

/out

0.28

-out

0.17

-Out

0.17

 ÙĪØ®

0.17

halb

0.17

.defaults

0.17

ARM

0.15

boss

0.15

dech

0.15

 parentheses

0.14

Activations Density 0.024%

instances of the word "inside" and variations of it in contexts discussing physical or metaphorical spaces

No Comments

No Known Activations