INDEX

Explanations

instances of specific and diverse word forms within technical or specialized text contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ovel

-0.17

elan

-0.16

thane

-0.15

IGN

-0.15

 Hiring

-0.15

imei

-0.14

 Gand

-0.14

Ð»Ð¸Ð½Ð¸

-0.14

_lineno

-0.14

Ð°Ð½Ð¸ÑĨ

-0.14

POSITIVE LOGITS

tero

0.14

ril

0.14

eldom

0.14

 Ð¶Ðµ

0.14

ertility

0.14

emonic

0.14

rust

0.14

Ø±Ø¬

0.14

etchup

0.14

Lau

0.14

Activations Density 0.004%

instances of specific and diverse word forms within technical or specialized text contexts

No Comments

No Known Activations