INDEX

Explanations

technical terms related to keyboard functionalities and shortcuts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

avig

-0.18

erif

-0.16

jedn

-0.15

znik

-0.15

upal

-0.14

aliz

-0.14

_tac

-0.14

classpath

-0.14

onas

-0.14

POSITIVE LOGITS

RK

0.15

sequences

0.15

_RADIUS

0.14

iger

0.14

 è¢

0.13

jis

0.13

.getUserId

0.13

asser

0.13

ack

0.12

Activations Density 0.044%

technical terms related to keyboard functionalities and shortcuts

No Comments

No Known Activations