INDEX

Explanations

concepts related to identity and self-expression

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

nen

-0.18

wert

-0.17

ampion

-0.15

nesia

-0.14

acht

-0.14

lernen

-0.14

esterday

-0.14

ipop

-0.13

 fold

-0.13

iment

-0.13

POSITIVE LOGITS

 personal

0.25

personal

0.21

 Personal

0.20

Personal

0.20

 self

0.18

åĢĭäºº

0.17

 pesso

0.17

 Ð»Ð¸Ñĩ

0.17

_self

0.17

 Self

0.17

Activations Density 0.297%

concepts related to identity and self-expression

No Comments

No Known Activations