INDEX

Explanations

punctuation marks or periods in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

edium

-0.16

kola

-0.14

lus

-0.14

inya

-0.14

usch

-0.13

oke

-0.13

efeller

-0.13

abad

-0.13

ARB

-0.13

bourne

-0.13

POSITIVE LOGITS

prec

0.15

 Lindsay

0.15

åİļ

0.14

exo

0.14

 Prec

0.14

expo

0.14

yu

0.14

iku

0.13

 Ivanka

0.13

 itir

0.13

Activations Density 0.031%

punctuation marks or periods in text

No Comments

No Known Activations