INDEX

Explanations

phrases and terms related to conditions, requirements, and modifications in agreements or plans

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

ãĥ³ãĥĸ

-0.15

È

-0.14

-urlencoded

-0.14

.Pages

-0.13

nex

-0.12

bee

-0.12

olon

-0.12

oker

-0.12

ndon

-0.12

.communication

-0.12

POSITIVE LOGITS

 above

1.34

above

1.15

 Above

1.07

Above

1.05

 ABOVE

0.98

 Ð²ÑĭÑĪÐµ

0.83

_above

0.82

 aforementioned

0.80

ä»¥ä¸Ĭ

0.79

bove

0.76

Activations Density 0.581%

phrases and terms related to conditions, requirements, and modifications in agreements or plans

No Comments

No Known Activations