INDEX

Explanations

programming constructs and settings in code snippets

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

Negative Logits

 unarmed

-0.17

night

-0.14

IsNull

-0.14

AndUpdate

-0.14

/exec

-0.13

lsen

-0.13

kuv

-0.13

Î³ÏģÎ¬

-0.13

_execute

-0.13

ego

-0.13

POSITIVE LOGITS

ECTOR

0.15

eshire

0.15

rox

0.15

cela

0.14

evice

0.14

ullo

0.14

rost

0.13

éĭ

0.13

onse

0.13

ycl

0.13

Activations Density 0.076%

programming constructs and settings in code snippets

No Known Activations