INDEX

Explanations

references to the word "ball" and its variations indicating its movement or properties

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

eme

-0.19

excel

-0.18

emed

-0.17

etto

-0.17

lessly

-0.17

datatable

-0.16

orex

-0.16

enance

-0.15

à¸Ħ

-0.15

forth

-0.15

POSITIVE LOGITS

room

0.24

istics

0.21

weg

0.20

antine

0.19

ISTIC

0.19

ustr

0.18

istic

0.18

er

0.18

-shaped

0.18

entine

0.17

Activations Density 0.032%

references to the word "ball" and its variations indicating its movement or properties

No Comments

No Known Activations