INDEX

Explanations

programming-related terms and code structure elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 NÄĽkter

-0.17

pagesize

-0.16

ÑĤÐ¸ÑĢÐ¾Ð²

-0.15

ortal

-0.15

 NÄĽk

-0.15

ç±

-0.14

ķãĤĵ

-0.14

 Pregn

-0.14

Å¡ek

-0.14

coni

-0.14

POSITIVE LOGITS

errick

0.15

 å¾

0.14

 embr

0.14

á»Ł

0.14

udge

0.14

Ih

0.14

rink

0.13

Ã³j

0.13

errat

0.13

Activations Density 0.190%

programming-related terms and code structure elements

No Comments

No Known Activations