INDEX

Explanations

references to specific films and the people associated with them

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

-0.16

aks

-0.16

ensor

-0.15

.Automation

-0.14

zar

-0.14

 Editorial

-0.14

Ups

-0.14

fold

-0.14

³

-0.14

inqu

-0.14

POSITIVE LOGITS

uther

0.17

emie

0.16

Å¼e

0.16

utin

0.15

.people

0.15

ardy

0.14

iyat

0.14

lest

0.14

ius

0.14

koneksi

0.14

Activations Density 0.003%

references to specific films and the people associated with them

No Comments

No Known Activations