INDEX

Explanations

phrases indicating a connection to specific categories or fields, particularly those ending with "-based."

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

mina

-0.18

chemas

-0.16

ursive

-0.14

oro

-0.14

lesi

-0.14

arra

-0.14

itespace

-0.14

ÑģÑĮÐ¾Ð³Ð¾

-0.14

ular

-0.13

urrection

-0.13

POSITIVE LOGITS

pson

0.16

rob

0.15

/-

0.14

etro

0.14

anie

0.14

Į¨

0.14

ieten

0.14

forces

0.14

ETER

0.14

ness

0.13

Activations Density 0.118%

phrases indicating a connection to specific categories or fields, particularly those ending with "-based."

No Comments

No Known Activations