INDEX

Explanations

proper nouns, particularly names and titles related to historical figures and scientific concepts

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

inee

-0.16

xing

-0.15

ÑĢÐ¸Ð·

-0.14

lei

-0.14

nds

-0.14

akhir

-0.14

porno

-0.14

å°ĭ

-0.14

igest

-0.14

avir

-0.14

POSITIVE LOGITS

ius

0.17

_SOC

0.16

gener

0.16

icz

0.15

ussy

0.15

elsius

0.15

 Memorial

0.15

bey

0.15

essel

0.14

Activations Density 0.262%

proper nouns, particularly names and titles related to historical figures and scientific concepts

No Comments

No Known Activations