INDEX

Explanations

concepts related to mathematical semantics and operator behavior in graph theory

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ä¾¡

-0.14

.messaging

-0.13

antine

-0.13

enso

-0.13

ope

-0.13

.builders

-0.13

ipp

-0.13

atch

-0.13

POSITIVE LOGITS

ardown

0.16

.Generated

0.15

erah

0.14

ols

0.13

åº«

0.13

_migration

0.13

ÏĦÏī

0.13

IRTUAL

0.13

rophe

0.13

.signals

0.12

Activations Density 0.099%

concepts related to mathematical semantics and operator behavior in graph theory

No Comments

No Known Activations