INDEX

Explanations

pronouns indicating the presence of a conversation or dialogue

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

tridge

-0.17

ajes

-0.16

 coin

-0.15

atham

-0.15

dain

-0.15

ongsTo

-0.15

_EST

-0.14

 atlas

-0.14

ingt

-0.14

Ð¾Ð½Ð´

-0.14

POSITIVE LOGITS

ken

0.19

ivor

0.16

arken

0.16

 finish

0.16

asio

0.16

reeze

0.16

Mini

0.15

inish

0.15

itre

0.15

mini

0.15

Activations Density 0.013%

pronouns indicating the presence of a conversation or dialogue

No Comments

No Known Activations