INDEX

Explanations

terms related to measurement and classification in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

-0.20

hook

-0.20

à¸£

-0.19

ings

-0.19

ing

-0.18

haf

-0.17

sar

-0.17

onet

-0.17

iest

-0.17

ein

-0.17

POSITIVE LOGITS

ALLY

0.60

ally

0.55

ity

0.37

amente

0.32

all

0.30

ITY

0.29

ated

0.26

ians

0.26

ities

0.25

us

0.24

Activations Density 0.231%

terms related to measurement and classification in various contexts

No Comments

No Known Activations