INDEX

Explanations

terms related to residency and residents in various contexts

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

rol

-0.15

osy

-0.15

quÃ©

-0.14

loth

-0.14

icorn

-0.14

otlin

-0.14

gee

-0.14

Ïħ

-0.14

osition

-0.13

ÏĢÎ·

-0.13

POSITIVE LOGITS

rieve

0.15

strict

0.14

 Schro

0.14

ials

0.14

ÏįÏĢ

0.14

lies

0.14

 Sylv

0.14

íĦ¸

0.14

 Sons

0.14

aldo

0.13

Activations Density 0.011%

terms related to residency and residents in various contexts

No Comments

No Known Activations