INDEX

Explanations

modal verbs indicating ability or possibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

phin

-0.15

 domicile

-0.14

Val

-0.14

ransition

-0.14

ecome

-0.14

Wunused

-0.13

/domain

-0.13

theast

-0.13

ampp

-0.13

hl

-0.13

POSITIVE LOGITS

 afford

0.21

 stomach

0.20

 somehow

0.18

opic

0.17

0.15

kuk

0.15

lek

0.15

AFF

0.15

 trust

0.14

acom

0.14

Activations Density 0.111%

modal verbs indicating ability or possibility

No Comments

No Known Activations