INDEX

Explanations

terms and concepts related to information retrieval and natural language processing systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

oner

-0.16

ereo

-0.15

prov

-0.15

idy

-0.14

 Temperature

-0.14

emperature

-0.14

owell

-0.14

 Problem

-0.14

 temperature

-0.13

/utility

-0.13

POSITIVE LOGITS

anol

0.20

inging

0.16

ollah

0.15

ssi

0.15

plex

0.15

seau

0.14

 Antwort

0.14

_NT

0.14

.tie

0.14

ç½®

0.14

Activations Density 0.187%

terms and concepts related to information retrieval and natural language processing systems

No Comments

No Known Activations