INDEX

Explanations

affirmative responses and positive confirmations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

hal

-0.17

ton

-0.17

ect

-0.16

loo

-0.15

weg

-0.15

jes

-0.14

lo

-0.14

uma

-0.14

cin

-0.14

pton

-0.14

POSITIVE LOGITS

enia

0.17

ÑĥÐ´Ð¸

0.17

Ģìŀ¥

0.17

nick

0.16

udas

0.16

indy

0.15

gor

0.15

agher

0.15

Bias

0.15

/false

0.15

Activations Density 0.043%

affirmative responses and positive confirmations

No Comments

No Known Activations