INDEX

Explanations

names of notable people, locations, and objects within specific contexts

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

inand

-0.15

esda

-0.14

roje

-0.14

Haj

-0.13

readcrumb

-0.13

å¤ªéĥİ

-0.13

zÃ¡

-0.13

sheets

-0.13

ocos

-0.13

POSITIVE LOGITS

ess

0.16

ilian

0.15

shire

0.15

ardo

0.15

pio

0.15

afen

0.15

erna

0.14

stry

0.14

ien

0.14

Mig

0.14

Activations Density 1.000%

names of notable people, locations, and objects within specific contexts

No Comments

No Known Activations