INDEX

Explanations

personal pronouns and related grammatical forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

kke

-0.17

ambil

-0.16

ff

-0.16

ÑģÑĮ

-0.16

oble

-0.14

alis

-0.14

oks

-0.14

assis

-0.14

hu

-0.14

ughter

-0.14

POSITIVE LOGITS

0.21

most

0.20

er

0.19

0.17

like

0.17

no

0.17

la

0.17

lings

0.17

standing

0.16

Activations Density 0.090%

personal pronouns and related grammatical forms

No Comments

No Known Activations