INDEX

Explanations

attributes and properties related to elements in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ersh

-0.16

ude

-0.15

inski

-0.15

luÅ¾

-0.15

lassen

-0.14

ins

-0.14

riel

-0.14

VEST

-0.14

daÅŁ

-0.14

 VÅ¡

-0.13

POSITIVE LOGITS

exion

0.16

 dout

0.15

implify

0.14

åĭ¢

0.14

aya

0.14

Ø¹Ø§

0.14

ocale

0.14

æ¹¯

0.13

adj

0.13

 Gloss

0.13

Activations Density 0.006%

attributes and properties related to elements in a programming context

No Comments

No Known Activations