INDEX

Explanations

past tense verbs and words that indicate the process of creation or development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

afort

-0.15

aeper

-0.14

kup

-0.14

loub

-0.13

Ø§ÙĪØª

-0.13

entiful

-0.13

ceased

-0.13

kara

-0.13

uba

-0.12

phia

-0.12

POSITIVE LOGITS

 created

0.41

 developed

0.35

 conco

0.35

 crafted

0.35

created

0.34

 conceived

0.33

 devised

0.33

 designed

0.32

 constructed

0.32

 conceptual

0.31

Activations Density 0.269%

past tense verbs and words that indicate the process of creation or development

No Comments

No Known Activations