INDEX

Explanations

instances of the pronoun "I" and related personal statements or reflections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ibold

-0.16

utan

-0.15

apon

-0.15

exo

-0.15

 Paper

-0.15

Ye

-0.14

Elapsed

-0.13

 Remarks

-0.13

AGON

-0.13

 Clay

-0.13

POSITIVE LOGITS

 ever

0.20

 memory

0.19

 hadn

0.19

 EVER

0.17

 correctly

0.17

memory

0.16

 entend

0.16

plx

0.15

 were

0.15

ëĿ¼ëıĦ

0.15

Activations Density 0.033%

instances of the pronoun "I" and related personal statements or reflections

No Comments

No Known Activations