INDEX

Explanations

infinitive verbs indicating a desire or intention

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

-0.16

 source

-0.16

blade

-0.15

nik

-0.15

-0.14

 deprived

-0.14

usu

-0.14

igon

-0.14

Ð¸ÐºÐ¸

-0.14

POSITIVE LOGITS

evin

0.15

Ø¨ÙĪØ±

0.15

á»ģn

0.15

 ÑĩÐ¸Ð¼

0.15

onse

0.15

enin

0.14

krom

0.14

.UnitTesting

0.14

ResponseStatus

0.14

Activations Density 0.006%

infinitive verbs indicating a desire or intention

No Comments

No Known Activations