INDEX

Explanations

adjectives that describe qualities or characteristics, particularly positive and impactful ones

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 Ð·Ð°ÐºÐ»Ð°Ð´

-0.18

swire

-0.17

ewire

-0.17

edia

-0.16

ued

-0.15

OLS

-0.15

Ã¡tek

-0.14

PIO

-0.14

atter

-0.14

ario

-0.14

POSITIVE LOGITS

geh

0.17

 caps

0.15

ÐµÑĢÐµ

0.15

rente

0.15

 Hung

0.14

 solid

0.14

 outright

0.14

ÑĤÑĶ

0.14

 Vance

0.14

Hag

0.14

Activations Density 0.688%

adjectives that describe qualities or characteristics, particularly positive and impactful ones

No Comments

No Known Activations