INDEX

Explanations

names and titles associated with people and organizations in cultural and political contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ittle

-0.26

ORA

-0.17

uur

-0.15

flen

-0.15

inish

-0.15

ç£

-0.15

plode

-0.14

å·

-0.14

ichick

-0.14

glm

-0.14

POSITIVE LOGITS

co

0.16

ign

0.15

ini

0.15

vo

0.15

ela

0.15

 affair

0.15

ola

0.14

beck

0.14

à¹ģà¸ķ

0.14

ercial

0.13

Activations Density 0.297%

names and titles associated with people and organizations in cultural and political contexts

No Comments

No Known Activations