INDEX

Explanations

names or references related to specific individuals or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

zte

-0.16

umper

-0.16

ki

-0.15

yan

-0.15

exion

-0.14

 hence

-0.14

ators

-0.14

QM

-0.14

ä»²

-0.14

WF

-0.14

POSITIVE LOGITS

htags

0.25

htag

0.23

bro

0.21

band

0.20

OwnProperty

0.19

imoto

0.19

brook

0.18

lett

0.17

peria

0.17

oldt

0.17

Activations Density 0.027%

names or references related to specific individuals or entities

No Comments

No Known Activations