INDEX

Explanations

programming-related settings for fields in a database model

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ms

-0.15

Col

-0.15

ãĥ¬ãĥĥãĥĪ

-0.15

ieee

-0.14

agh

-0.14

uries

-0.14

_smart

-0.14

iros

-0.14

dbl

-0.13

actices

-0.13

POSITIVE LOGITS

à¹Īà¸Ńà¸¡

0.17

ificate

0.15

cem

0.14

-rad

0.13

Late

0.13

.jpa

0.13

à¤¬à¤²

0.13

Leaks

0.13

ounce

0.13

ÙĪØ°

0.13

Activations Density 0.012%

programming-related settings for fields in a database model

No Comments

No Known Activations