INDEX

Explanations

programming constructs related to type definitions and structure in a code 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

iver

-0.17

adol

-0.16

idas

-0.15

 Bucc

-0.15

ader

-0.15

ulan

-0.15

chwitz

-0.14

ingo

-0.14

addock

-0.14

inja

-0.14

POSITIVE LOGITS

é§Ĳ

0.15

ãĥ³ãĤ¿

0.14

iams

0.14

ONGLONG

0.14

enet

0.14

°ëĭ¤

0.14

.defer

0.14

veloper

0.14

 Ø²Ùħ

0.13

Activations Density 0.001%

programming constructs related to type definitions and structure in a code context

No Comments

No Known Activations