INDEX

Explanations

first-person pronouns indicating personal experiences and opinions

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

lix

-0.15

lobe

-0.14

HEMA

-0.14

;element

-0.14

cdb

-0.14

oredProcedure

-0.14

Await

-0.14

 Ð·Ð°Ð²Ð¸

-0.14

spender

-0.13

plet

-0.13

POSITIVE LOGITS

ronic

0.27

 mean

0.25

ck

0.23

.e

0.22

 even

0.20

kid

0.19

bet

0.18

 joke

0.18

even

0.18

Activations Density 0.184%

first-person pronouns indicating personal experiences and opinions

No Comments

No Known Activations