INDEX

Explanations

proper nouns associated with specific projects or people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

us

-0.21

_queries

-0.18

ues

-0.15

 FILES

-0.15

Sas

-0.15

asaki

-0.15

ÑģÑıÑĤ

-0.15

éķ

-0.15

STALL

-0.15

_us

-0.15

POSITIVE LOGITS

mans

0.32

ands

0.29

iams

0.29

rens

0.28

ends

0.27

olds

0.27

inds

0.26

ards

0.26

ords

0.26

unds

0.26

Activations Density 0.234%

proper nouns associated with specific projects or people

No Comments

No Known Activations