INDEX

Explanations

instances of the word "in" and similar prepositions within complex phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

 scale

-0.15

 conflicts

-0.15

embers

-0.15

Wheel

-0.15

Moo

-0.15

onom

-0.14

 ÑĥÑħ

-0.14

Ð½Ñĥ

-0.14

tip

-0.14

ÙĲÙĩ

-0.14

POSITIVE LOGITS

hiba

0.17

ictor

0.17

adium

0.15

ixin

0.14

 Schmidt

0.14

 comprom

0.14

inel

0.14

.sharedInstance

0.13

ascade

0.13

ges

0.13

Activations Density 0.508%

instances of the word "in" and similar prepositions within complex phrases

No Comments

No Known Activations