INDEX

Explanations

elements related to programming syntax, specifically concerning data types and structures

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

Å¾ila

-0.16

 Bilim

-0.16

esis

-0.15

oup

-0.15

alette

-0.15

esi

-0.15

æĮ¯ãĤĬ

-0.14

.notNull

-0.14

(strip

-0.14

lund

-0.14

POSITIVE LOGITS

cheng

0.18

ki

0.15

agra

0.15

 Crosby

0.15

ilton

0.15

andon

0.14

ami

0.14

ÏĥÏī

0.14

appers

0.14

iman

0.13

Activations Density 0.009%

elements related to programming syntax, specifically concerning data types and structures

No Comments

No Known Activations