INDEX

Explanations

programming concepts and terminology related to data structures and algorithms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 STACK

-0.19

PILE

-0.18

STACK

-0.18

 seins

-0.18

complexType

-0.17

åĽ²

-0.17

StackSize

-0.17

_indent

-0.16

urrenc

-0.15

GuidId

-0.15

POSITIVE LOGITS

 table

0.22

 keys

0.20

 bloom

0.19

 Collision

0.19

table

0.18

hit

0.18

keys

0.18

 hits

0.18

 leaf

0.17

hit

0.17

Activations Density 0.052%

programming concepts and terminology related to data structures and algorithms

No Comments

No Known Activations