INDEX

Explanations

programming-related keywords and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

phinx

-0.15

 ÐľÑĥ

-0.14

CAST

-0.14

estre

-0.14

uhl

-0.14

jab

-0.14

Dyn

-0.14

ael

-0.14

 Ð²ÑĸÑĤ

-0.14

mul

-0.13

POSITIVE LOGITS

udes

0.16

edia

0.15

 Burk

0.14

ordova

0.14

Moy

0.14

Zwe

0.14

ometr

0.14

 Send

0.14

undra

0.14

Messenger

0.13

Activations Density 0.028%

programming-related keywords and functions

No Comments

No Known Activations