INDEX

Explanations

terms related to average measurements or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 crack

-0.17

amework

-0.16

lien

-0.14

yth

-0.14

 dotted

-0.14

inez

-0.14

amient

-0.13

 white

-0.13

ileen

-0.13

POSITIVE LOGITS

IFO

0.17

ohl

0.15

abee

0.15

zda

0.15

ConverterFactory

0.14

ÙĨØ³

0.14

idis

0.14

ippet

0.14

endon

0.14

ensus

0.14

Activations Density 0.072%

terms related to average measurements or statistics

No Comments

No Known Activations