INDEX

Explanations

expressions and concepts related to honesty and integrity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

hin

-0.17

umba

-0.16

urge

-0.15

sko

-0.14

_simps

-0.14

NotificationCenter

-0.14

athers

-0.14

aan

-0.14

ils

-0.14

 Precision

-0.14

POSITIVE LOGITS

bones

0.17

OTES

0.15

ably

0.14

Ð»Ð¸Ð²

0.14

chaft

0.14

 Vanilla

0.14

 faker

0.14

oday

0.14

ycastle

0.14

 about

0.14

Activations Density 0.014%

expressions and concepts related to honesty and integrity

No Comments

No Known Activations