INDEX

Explanations

specific names and identifiers related to individuals and their roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

icha

-0.15

ropp

-0.14

æŃ

-0.14

à¸´à¹Ī

-0.14

zer

-0.13

otel

-0.13

ç»

-0.12

odom

-0.12

adoo

-0.12

alm

-0.12

POSITIVE LOGITS

 left

0.57

 center

0.56

 centre

0.52

 right

0.50

left

0.46

center

0.43

centre

0.41

far

0.40

right

0.40

 foreground

0.40

Activations Density 0.105%

specific names and identifiers related to individuals and their roles

No Comments

No Known Activations