INDEX

Explanations

references to ethical or moral dilemmas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

which

-0.18

.scalablytyped

-0.17

 which

-0.17

atever

-0.16

 Î¿ÏĢÎ¿Î¯Î±

-0.15

 WHICH

-0.15

quel

-0.15

 rencont

-0.15

-0.14

uments

-0.14

POSITIVE LOGITS

 neither

0.19

 essence

0.18

icable

0.17

ess

0.16

 nobody

0.16

arg

0.16

bidden

0.15

esc

0.15

tring

0.15

 fact

0.15

Activations Density 0.239%

references to ethical or moral dilemmas

No Comments

No Known Activations