INDEX

Explanations

technical language related to programming or software configuration

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

insk

-0.18

iola

-0.16

onis

-0.15

Gig

-0.14

rove

-0.14

isser

-0.14

deck

-0.14

juana

-0.14

inh

-0.14

POSITIVE LOGITS

legen

0.17

LOPT

0.16

0.15

yu

0.14

cop

0.14

Sensor

0.14

ÐµÑĢÐ°Ð»ÑĮ

0.14

 Sensors

0.14

gomery

0.14

MSN

0.14

Activations Density 0.029%

technical language related to programming or software configuration

No Comments

No Known Activations