INDEX

Explanations

phrases related to the understanding and analysis of scientific concepts in engineering and environmental contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 fiat

-0.14

 conven

-0.14

Type

-0.13

 reck

-0.13

lient

-0.13

 insensitive

-0.13

pun

-0.13

aud

-0.13

POSITIVE LOGITS

 dynamics

0.30

 properties

0.29

 relationships

0.28

 Dynamics

0.26

properties

0.26

 mechanisms

0.25

 behavior

0.25

 patterns

0.24

-properties

0.24

 behaviour

0.24

Activations Density 0.345%

phrases related to the understanding and analysis of scientific concepts in engineering and environmental contexts

No Comments

No Known Activations