INDEX

Explanations

variations of the verb "be," particularly in different tenses and contexts indicating existence or qualities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

-0.15

oned

-0.14

oppins

-0.14

 Fisher

-0.14

cheng

-0.13

 hell

-0.13

ches

-0.13

POSITIVE LOGITS

friend

0.16

croft

0.16

GINE

0.16

eline

0.15

eo

0.15

ouz

0.15

ethoven

0.14

 patient

0.14

atrix

0.14

ardless

0.14

Activations Density 0.124%

variations of the verb "be," particularly in different tenses and contexts indicating existence or qualities

No Comments

No Known Activations