INDEX

Explanations

code-related terms and structures within programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 barn

-0.14

erp

-0.14

ong

-0.14

 McDon

-0.13

ause

-0.13

lector

-0.13

 Äĳáº¡i

-0.13

 è¾

-0.13

POSITIVE LOGITS

ä¼Ļ

0.21

linky

0.17

HAL

0.16

TypeDef

0.16

hal

0.16

ahren

0.15

icens

0.15

 BaseType

0.15

RTOS

0.15

0.14

Activations Density 0.072%

code-related terms and structures within programming contexts

No Comments

No Known Activations