INDEX

Explanations

negative phrases or words expressing denial and absence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

rary

-0.16

ipsis

-0.16

noon

-0.15

iÃ¨me

-0.15

loo

-0.15

gio

-0.14

nist

-0.14

iguous

-0.14

encers

-0.14

stants

-0.14

POSITIVE LOGITS

 matter

0.44

 amount

0.36

matter

0.30

 Matter

0.27

amount

0.26

 doubt

0.25

 wonder

0.23

-body

0.23

-one

0.23

 Amount

0.23

Activations Density 0.044%

negative phrases or words expressing denial and absence

No Comments

No Known Activations