INDEX

Explanations

words related to official documents or publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

orr

-0.17

onder

-0.16

scalar

-0.15

/XMLSchema

-0.15

kud

-0.15

iddle

-0.14

erior

-0.14

#/

-0.14

 Jury

-0.14

illac

-0.14

POSITIVE LOGITS

 Lind

0.17

ilden

0.16

enko

0.15

ÏĦÎ¿Îº

0.15

0.14

 Lesser

0.14

 Grove

0.14

bsolute

0.14

UIS

0.14

terra

0.13

Activations Density 0.001%

words related to official documents or publications

No Comments

No Known Activations