INDEX

Explanations

occurrences of the prefix 'inc' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

åĺ

-0.15

othy

-0.15

stretch

-0.15

lie

-0.15

trand

-0.15

.cz

-0.14

las

-0.14

INGS

-0.14

eness

-0.14

ÑĤÑĮ

-0.14

POSITIVE LOGITS

ognito

0.28

inc

0.25

ipient

0.24

identally

0.23

ogn

0.23

obot

0.21

iner

0.21

/inc

0.20

idental

0.20

Inc

0.20

Activations Density 0.021%

occurrences of the prefix 'inc' in various contexts

No Comments

No Known Activations