INDEX

Explanations

possessive forms or contractions indicating ownership or belonging

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

iyon

-0.17

Ãºp

-0.14

kich

-0.14

asant

-0.14

idl

-0.14

Ĥ¬

-0.13

nano

-0.13

Independ

-0.13

kaar

-0.13

uran

-0.13

POSITIVE LOGITS

Ä±rak

0.16

\Php

0.15

ucks

0.15

/autoload

0.15

asti

0.14

andler

0.14

 gode

0.14

ASTE

0.14

clerosis

0.14

 bach

0.14

Activations Density 0.156%

possessive forms or contractions indicating ownership or belonging

No Comments

No Known Activations