INDEX

Explanations

references to novels and literary works

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

esson

-0.15

æŁ´

-0.14

odal

-0.14

inder

-0.14

ç«ĭ

-0.14

ultural

-0.13

ung

-0.13

plier

-0.13

nio

-0.13

Tot

-0.13

POSITIVE LOGITS

icker

0.18

abyrin

0.15

illos

0.15

ãĥĥãĥĦ

0.15

atile

0.15

UIFont

0.14

ynes

0.14

caa

0.14

vest

0.14

iefs

0.13

Activations Density 0.047%

references to novels and literary works

No Known Activations