INDEX

Explanations

themes related to transformation and redemption

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

leans

-0.17

angent

-0.15

gnore

-0.15

adro

-0.14

undry

-0.14

çµµ

-0.14

 spoluprÃ¡ci

-0.14

ÑĩÐ¸Ñħ

-0.13

oise

-0.13

 hoop

-0.13

POSITIVE LOGITS

adero

0.17

itta

0.16

tec

0.16

.SO

0.16

 opposite

0.15

0.14

rus

0.14

esign

0.14

oyo

0.14

Activations Density 0.296%

themes related to transformation and redemption

No Comments

No Known Activations