INDEX

Explanations

occurrences of the word "I" and related personal pronouns indicating self-reference

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

igo

-0.17

è®©æĪĳ

-0.16

 myself

-0.15

ãĥ¼ãĥĢ

-0.14

ceased

-0.14

ynet

-0.14

’da

-0.13

’na

-0.13

Î¹

-0.13

 Admir

-0.13

POSITIVE LOGITS

 plan

0.23

plan

0.20

 think

0.19

 haven

0.18

Think

0.17

may

0.17

 figure

0.17

 finally

0.16

 hope

0.16

iswa

0.16

Activations Density 0.229%

occurrences of the word "I" and related personal pronouns indicating self-reference

No Comments

No Known Activations