INDEX

Explanations

connector words and conjunctions indicating options or choices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ãĤ¦ãĥĪ

-0.15

otros

-0.15

ÐºÑĥÐ»

-0.14

nict

-0.14

ê¸ī

-0.14

oS

-0.14

enor

-0.14

earth

-0.14

/uploads

-0.14

çĽ®

-0.14

POSITIVE LOGITS

ignal

0.20

anged

0.19

ourke

0.19

 Bust

0.17

 bust

0.17

ator

0.16

leans

0.16

lando

0.15

hana

0.15

tel

0.15

Activations Density 0.090%

connector words and conjunctions indicating options or choices

No Comments

No Known Activations