INDEX

Explanations

references to self-acceptance and personal growth

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

 Synd

-0.16

 ç¯

-0.14

å±Ģ

-0.14

 synd

-0.14

æµ¦

-0.13

sak

-0.13

á»Ľt

-0.13

IRR

-0.13

loquent

-0.13

gon

-0.13

POSITIVE LOGITS

Ã²i

0.14

OMIC

0.14

 Physical

0.14

colo

0.13

ativa

0.13

 TORT

0.13

Ð»ÑİÑĩÐ°

0.13

ç°

0.13

Hun

0.13

facebook

0.13

Activations Density 0.173%

references to self-acceptance and personal growth

No Comments

No Known Activations