INDEX

Explanations

references to personal ownership and individual contribution in discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

angler

-0.16

ê¶ģ

-0.15

ãģĭãģ«

-0.14

ifo

-0.14

ander

-0.14

placeholders

-0.13

ÐµÐºÑģÐ¸

-0.13

ÃŃÅ¡

-0.13

mdp

-0.13

postalcode

-0.13

POSITIVE LOGITS

own

1.37

own

1.06

Own

1.05

èĩªå·±çļĦ

0.98

Own

0.97

OWN

0.94

 prÃ³p

0.90

_own

0.87

 eigenen

0.85

 propia

0.79

Activations Density 0.437%

references to personal ownership and individual contribution in discussions

No Comments

No Known Activations