INDEX

Explanations

references to an increase or arrival of people or things into a location or system

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

iro

-0.17

erk

-0.16

fold

-0.15

 Slut

-0.15

ieves

-0.15

zt

-0.14

zv

-0.14

éĴŁ

-0.14

igi

-0.13

bies

-0.13

POSITIVE LOGITS

0.17

ETERS

0.16

gaard

0.16

enaire

0.15

quier

0.15

esin

0.15

yne

0.15

pdev

0.14

 Corm

0.14

 unst

0.13

Activations Density 0.004%

references to an increase or arrival of people or things into a location or system

No Comments

No Known Activations