INDEX

Explanations

infinitives and gerunds indicating actions or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

argar

-0.15

ALA

-0.15

ÐµÐ»Ð¾Ð²

-0.14

ear

-0.14

DataTask

-0.14

 Donovan

-0.14

_LOCK

-0.14

alis

-0.14

ecer

-0.14

endor

-0.14

POSITIVE LOGITS

loh

0.19

asu

0.18

aptor

0.16

izzo

0.16

rzy

0.16

edis

0.15

>manual

0.14

iaux

0.14

loor

0.14

ailed

0.14

Activations Density 0.050%

infinitives and gerunds indicating actions or processes

No Comments

No Known Activations