INDEX

Explanations

programming-related syntax and methods within code

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

indows

-0.16

isas

-0.15

oftware

-0.14

insi

-0.14

 Engel

-0.14

enek

-0.14

 authDomain

-0.14

lege

-0.14

 komb

-0.14

Exporter

-0.14

POSITIVE LOGITS

acin

0.17

quist

0.14

å¹¹

0.14

Ø³Ø§Ø²ÛĮ

0.13

unkt

0.13

áº¡ch

0.13

nos

0.13

abin

0.13

ullet

0.13

ienen

0.13

Activations Density 0.109%

programming-related syntax and methods within code

No Comments

No Known Activations