INDEX

Explanations

code-related constructs and operations involving object properties and methods

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

urdu

-0.15

ãģıãĤĭ

-0.15

lett

-0.15

ÅĽli

-0.15

lush

-0.15

inspace

-0.15

vre

-0.14

audi

-0.14

uner

-0.14

_shortcode

-0.14

POSITIVE LOGITS

erif

0.18

ityEngine

0.16

cai

0.15

ģm

0.15

çĺ

0.14

TEL

0.14

legates

0.14

gang

0.14

fon

0.14

opensource

0.13

Activations Density 0.240%

code-related constructs and operations involving object properties and methods

No Comments

No Known Activations