INDEX

Explanations

references to causation and causal relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ç¶

-0.16

MMC

-0.16

ynch

-0.14

IPA

-0.14

 Lair

-0.14

CellValue

-0.14

IPA

-0.14

 Kaynak

-0.14

ibel

-0.14

hausen

-0.13

POSITIVE LOGITS

cka

0.16

 Intelligence

0.16

exo

0.15

.scalablytyped

0.15

 Barrett

0.15

Jer

0.15

Bon

0.14

aha

0.14

íķĺìļ°

0.14

 grounds

0.14

Activations Density 0.020%

references to causation and causal relationships

No Comments

No Known Activations