INDEX

Explanations

names or references related to specific locations 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 @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

éĸ

-0.18

eros

-0.16

 éĸ

-0.16

å¨

-0.15

imd

-0.14

 Mines

-0.14

unction

-0.14

eri

-0.14

hait

-0.14

 ÙĨÙģ

-0.14

POSITIVE LOGITS

anooga

0.28

ahoo

0.20

emoc

0.19

jee

0.17

illon

0.16

enever

0.16

elier

0.16

opher

0.16

urved

0.16

oyer

0.15

Activations Density 0.017%

names or references related to specific locations or entities

No Comments

No Known Activations