INDEX

Explanations

structured data elements related to events in a dataset

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ignon

-0.14

ensa

-0.14

Mig

-0.14

unc

-0.14

enze

-0.13

mrt

-0.13

otto

-0.13

ØªØ±ÛĮ

-0.13

 verk

-0.13

/rfc

-0.13

POSITIVE LOGITS

çĿ

0.16

inding

0.15

ullets

0.15

 Becker

0.15

ulet

0.14

anges

0.14

getattr

0.14

.commons

0.14

0.13

horse

0.13

Activations Density 0.028%

structured data elements related to events in a dataset

No Comments

No Known Activations