INDEX

Explanations

queries and responses 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 @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

[=[

-0.14

orthand

-0.14

AsStringAsync

-0.13

amework

-0.13

AGMA

-0.13

ÑĢÑı

-0.13

gettext

-0.12

Å¡ov

-0.12

.ObjectId

-0.12

CAF

-0.12

POSITIVE LOGITS

 Node

0.49

 node

0.48

Node

0.46

node

0.44

_node

0.42

 nodes

0.42

 Nodes

0.41

 newNode

0.41

.Node

0.41

-node

0.41

Activations Density 0.040%

queries and responses related to data structures and algorithms

No Comments

No Known Activations