INDEX

Explanations

terms related to positioning in a programming or graphical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

AtPath

-0.15

agi

-0.15

osc

-0.15

ilim

-0.14

 sonu

-0.14

 setHidden

-0.13

ç¬Ķ

-0.13

Zem

-0.13

peater

-0.13

 SUBSTITUTE

-0.13

POSITIVE LOGITS

anford

0.16

olla

0.16

erif

0.15

 Lions

0.15

 getPosition

0.15

 lions

0.14

noun

0.14

andest

0.14

UNC

0.14

isia

0.14

Activations Density 0.030%

terms related to positioning in a programming or graphical context

No Comments

No Known Activations