INDEX

Explanations

possessive pronouns used in a context relating to individuals and their relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

apore

-0.16

Ð°Ð½Ð³

-0.15

isci

-0.15

 cáº£nh

-0.14

.second

-0.14

atted

-0.14

stral

-0.14

avers

-0.14

erable

-0.13

POSITIVE LOGITS

 troop

0.15

redi

0.15

ÏģÏī

0.14

 correspond

0.14

 audience

0.14

nech

0.14

 Male

0.14

 acceler

0.14

 Higher

0.14

æŀļ

0.13

Activations Density 0.122%

possessive pronouns used in a context relating to individuals and their relationships

No Comments

No Known Activations