INDEX

Explanations

names, titles, and identifiers related to individuals or entities

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

odos

-0.15

Ð¸ÑĨÐ¸Ð½

-0.15

vie

-0.15

undry

-0.15

chrift

-0.15

isure

-0.15

Jar

-0.15

laz

-0.14

.unsplash

-0.14

SEMB

-0.14

POSITIVE LOGITS

ayet

0.17

Ã¼p

0.15

Ã©ri

0.15

ova

0.15

ardo

0.14

vÄĽÅĻ

0.14

ertz

0.14

roti

0.14

.bind

0.14

arna

0.14

Activations Density 0.695%

names, titles, and identifiers related to individuals or entities

No Comments

No Known Activations