INDEX

Explanations

phrases indicating conditions or stipulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

phans

-0.18

ses

-0.17

ients

-0.15

rael

-0.15

á»¡

-0.15

mill

-0.14

shan

-0.14

eron

-0.14

ampie

-0.14

POSITIVE LOGITS

oret

0.31

adays

0.26

gether

0.26

oretical

0.26

atre

0.23

bidden

0.20

etheless

0.20

jourd

0.19

ÑįÑĤÐ¾Ð¼Ñĥ

0.18

odore

0.18

Activations Density 0.138%

phrases indicating conditions or stipulations

No Comments

No Known Activations