INDEX

Explanations

location and contact information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

menu

-0.15

ÏĢÎ¿Ïį

-0.14

-League

-0.14

emente

-0.14

md

-0.14

mant

-0.14

mai

-0.14

mate

-0.14

mÃ©

-0.14

POSITIVE LOGITS

Mor

1.45

Mor

1.45

mor

1.41

MOR

1.34

mor

1.23

 Morris

1.21

 ÐľÐ¾ÑĢ

1.06

 morph

1.01

 morality

0.97

 Morph

0.96

Activations Density 0.060%

location and contact information

No Comments

No Known Activations