INDEX

Explanations

occurrences of the verb "is" and its variations, reflecting states or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

Äįet

-0.17

TRACT

-0.15

ÑģÑĤÐ¸Ñĩ

-0.14

antu

-0.14

.onDestroy

-0.14

æŀ¶

-0.14

orts

-0.14

ascus

-0.14

ipur

-0.14

hin

-0.14

POSITIVE LOGITS

ewan

0.15

ocos

0.15

ni

0.14

mu

0.14

arak

0.14

ako

0.14

oston

0.14

.mu

0.13

ews

0.13

elta

0.13

Activations Density 0.053%

occurrences of the verb "is" and its variations, reflecting states or conditions

No Comments

No Known Activations