INDEX

Explanations

expressions of appreciation and feedback in communication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

-0.15

entanyl

-0.14

peq

-0.14

azy

-0.14

ÅĻet

-0.14

encial

-0.14

 gridColumn

-0.14

ÐºÐ°Ð¿

-0.14

ãĥ³ãĥĨ

-0.14

à¸¢à¸ģ

-0.14

POSITIVE LOGITS

ja

0.15

amo

0.15

Äį

0.15

oten

0.14

agra

0.14

ala

0.14

 provoc

0.14

 increasingly

0.14

 colleague

0.14

nto

0.14

Activations Density 0.020%

expressions of appreciation and feedback in communication

No Comments

No Known Activations