INDEX

Explanations

references to aspirations and positivity in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

orks

-0.16

ault

-0.16

anst

-0.14

 PartialView

-0.13

ectar

-0.13

fact

-0.13

ewater

-0.13

ÏģÎ¿Ïħ

-0.13

sok

-0.13

à¸©

-0.13

POSITIVE LOGITS

owo

0.16

Opp

0.14

tel

0.14

ilde

0.14

/template

0.14

Uph

0.14

Cro

0.14

 Chall

0.14

 Merry

0.14

Activations Density 0.061%

references to aspirations and positivity in various contexts

No Comments

No Known Activations