INDEX

Explanations

references to concepts of awareness and identity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 (...

-0.15

andr

-0.15

bÃŃr

-0.14

ĵåĲį

-0.14

 ÑĢÐ°Ð²

-0.13

endoza

-0.13

oyer

-0.13

 controlId

-0.13

estruct

-0.13

POSITIVE LOGITS

 slave

0.21

 Slave

0.19

 slaves

0.19

slave

0.19

Slave

0.18

 Gore

0.17

 tarn

0.16

arlar

0.15

Kur

0.15

 sandals

0.15

Activations Density 0.004%

references to concepts of awareness and identity

No Comments

No Known Activations